Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.5273. Min Act: -0.1700
Data Index: 4831047 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.4333. Min Act: -0.1700
Data Index: 4921128 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.4177. Min Act: -0.1700
Data Index: 2327394 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.4333. Min Act: -0.1700
Data Index: 1929796 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.3863. Min Act: -0.1700
Data Index: 4441013 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.3549. Min Act: -0.1700
Data Index: 1215480 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.3549. Min Act: -0.1700
Data Index: 1512481 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.3392. Min Act: -0.1700
Data Index: 302401 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.3392. Min Act: -0.1700
Data Index: 310317 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.3079. Min Act: -0.1700
Data Index: 2080985 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.2922. Min Act: -0.1700
Data Index: 8747953 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.3079. Min Act: -0.1700
Data Index: 6050245 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.3079. Min Act: -0.1700
Data Index: 8699310 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.2922. Min Act: -0.1700
Data Index: 583111 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.2922. Min Act: -0.1700
Data Index: 3683515 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.2922. Min Act: -0.1700
Data Index: 968503 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.2765. Min Act: -0.1700
Data Index: 373843 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.2450. Min Act: -0.1700
Data Index: 3901950 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.2608. Min Act: -0.1700
Data Index: 2917152 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5273. Min Range: -3.5273
Max Act: 3.2765. Min Act: -0.1700
Data Index: 4121185 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19