Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.2041. Min Act: -0.1700
Data Index: 6420181 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.1103. Min Act: -0.1700
Data Index: 586171 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.1103. Min Act: -0.1700
Data Index: 6695384 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0791. Min Act: -0.1700
Data Index: 3046755 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0791. Min Act: -0.1700
Data Index: 3026977 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0478. Min Act: -0.1700
Data Index: 6865793 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2041. Min Range: -5.2041
Max Act: 5.0166. Min Act: -0.1700
Data Index: 437871 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9853. Min Act: -0.1700
Data Index: 3072900 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9853. Min Act: -0.1700
Data Index: 7740081 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9853. Min Act: -0.1700
Data Index: 4810515 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9541. Min Act: -0.1700
Data Index: 384178 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.9228. Min Act: -0.1700
Data Index: 5989526 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.8916. Min Act: -0.1700
Data Index: 7429127 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.8916. Min Act: -0.1700
Data Index: 5351000 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.8916. Min Act: -0.1700
Data Index: 6743763 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.8603. Min Act: -0.1700
Data Index: 2422742 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.8603. Min Act: -0.1700
Data Index: 3383113 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.8291. Min Act: -0.1700
Data Index: 1962157 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.8603. Min Act: -0.1700
Data Index: 2017995 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2041. Min Range: -5.2041
Max Act: 4.8603. Min Act: -0.1700
Data Index: 1375813 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19