Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4742 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0465. Min Range: -3.0465
Max Act: 3.0465. Min Act: -0.1700
Data Index: 3793600 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.9516. Min Act: -0.1700
Data Index: 1398608 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.9200. Min Act: -0.1700
Data Index: 5898552 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.9358. Min Act: -0.1700
Data Index: 4546003 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.9041. Min Act: -0.1700
Data Index: 3796483 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.9041. Min Act: -0.1700
Data Index: 4986675 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8883. Min Act: -0.1700
Data Index: 7880288 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8883. Min Act: -0.1700
Data Index: 8323254 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8565. Min Act: -0.1700
Data Index: 6138714 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8406. Min Act: -0.1700
Data Index: 8129450 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8247. Min Act: -0.1700
Data Index: 1342432 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8247. Min Act: -0.1700
Data Index: 3733865 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.7929. Min Act: -0.1700
Data Index: 4820831 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8088. Min Act: -0.1700
Data Index: 24419 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8088. Min Act: -0.1700
Data Index: 8376190 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8088. Min Act: -0.1700
Data Index: 3934763 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8088. Min Act: -0.1700
Data Index: 707653 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.8247. Min Act: -0.1700
Data Index: 3081769 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.7929. Min Act: -0.1700
Data Index: 863823 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0465. Min Range: -3.0465
Max Act: 2.7610. Min Act: -0.1700
Data Index: 5426986 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19