Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.9263. Min Act: -0.1700
Data Index: 7081666 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.8326. Min Act: -0.1700
Data Index: 8123961 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.7076. Min Act: -0.1700
Data Index: 3151613 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6763. Min Act: -0.1700
Data Index: 6163093 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 3974380 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 3660672 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6451. Min Act: -0.1700
Data Index: 6087315 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6138. Min Act: -0.1700
Data Index: 5750211 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6138. Min Act: -0.1700
Data Index: 7405172 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6138. Min Act: -0.1700
Data Index: 2267350 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6138. Min Act: -0.1700
Data Index: 5756442 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.5826. Min Act: -0.1700
Data Index: 1704098 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.6138. Min Act: -0.1700
Data Index: 1938303 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.5826. Min Act: -0.1700
Data Index: 1099963 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.5513. Min Act: -0.1700
Data Index: 7927376 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.5513. Min Act: -0.1700
Data Index: 5679386 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.5826. Min Act: -0.1700
Data Index: 6802179 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.5513. Min Act: -0.1700
Data Index: 4501512 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.5513. Min Act: -0.1700
Data Index: 8269825 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9263. Min Range: -4.9263
Max Act: 4.5513. Min Act: -0.1700
Data Index: 6966936 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19