Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2179 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.8041. Min Act: -0.1700
Data Index: 5054322 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.8041. Min Act: -0.1700
Data Index: 7529795 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.6166. Min Act: -0.1695
Data Index: 5810931 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.6166. Min Act: -0.1700
Data Index: 4178585 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.6166. Min Act: -0.1700
Data Index: 4389872 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.6166. Min Act: -0.1658
Data Index: 4880009 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.6166. Min Act: -0.1696
Data Index: 5461514 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.6166. Min Act: -0.1658
Data Index: 8123146 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.5541. Min Act: -0.1695
Data Index: 1128852 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.5541. Min Act: -0.1700
Data Index: 5101549 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.4916. Min Act: -0.1691
Data Index: 2439591 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.4916. Min Act: -0.1689
Data Index: 2165605 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.5541. Min Act: -0.1700
Data Index: 5252200 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.4916. Min Act: -0.1693
Data Index: 1731938 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.4291. Min Act: -0.1700
Data Index: 516321 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.4291. Min Act: -0.1700
Data Index: 3166199 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.4291. Min Act: -0.1099
Data Index: 3272397 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.4291. Min Act: -0.1700
Data Index: 4129088 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.3666. Min Act: -0.1693
Data Index: 1469670 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.8041. Min Range: -13.8041
Max Act: 13.4291. Min Act: -0.1700
Data Index: 731829 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19