Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1662 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.9353. Min Act: -0.1700
Data Index: 4645010 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.8416. Min Act: -0.1700
Data Index: 1877732 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.5916. Min Act: -0.1700
Data Index: 381904 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.6228. Min Act: -0.1700
Data Index: 2245613 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.4353. Min Act: -0.1700
Data Index: 2380939 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.4978. Min Act: -0.1700
Data Index: 4743963 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.5916. Min Act: -0.1700
Data Index: 8174589 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.5603. Min Act: -0.1700
Data Index: 4874796 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.5291. Min Act: -0.1700
Data Index: 3426075 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.5291. Min Act: -0.1700
Data Index: 4938534 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.5916. Min Act: -0.1700
Data Index: 6805300 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.4666. Min Act: -0.1700
Data Index: 1868703 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.4041. Min Act: -0.1700
Data Index: 7804532 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.4353. Min Act: -0.1700
Data Index: 4112677 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.4041. Min Act: -0.1700
Data Index: 2512189 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.4041. Min Act: -0.1700
Data Index: 2402615 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.4041. Min Act: -0.1700
Data Index: 4657123 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.3416. Min Act: -0.1700
Data Index: 7588322 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.3416. Min Act: -0.1700
Data Index: 5713254 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9353. Min Range: -6.9353
Max Act: 6.3416. Min Act: -0.1700
Data Index: 4549072 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19