Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 583 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.4398. Min Act: -0.1700
Data Index: 6411662 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.4085. Min Act: -0.1700
Data Index: 1810668 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.3460. Min Act: -0.1700
Data Index: 8477961 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.3148. Min Act: -0.1700
Data Index: 4813981 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1897. Min Act: -0.1700
Data Index: 3023610 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1897. Min Act: -0.1700
Data Index: 1521413 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1897. Min Act: -0.1700
Data Index: 728188 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1585. Min Act: -0.1700
Data Index: 7948784 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1585. Min Act: -0.1700
Data Index: 6846080 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1272. Min Act: -0.1700
Data Index: 6502571 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1272. Min Act: -0.1700
Data Index: 8759383 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1272. Min Act: -0.1700
Data Index: 6517444 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.0960. Min Act: -0.1700
Data Index: 8142612 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.1272. Min Act: -0.1700
Data Index: 1670317 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.0960. Min Act: -0.1700
Data Index: 8315981 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.0647. Min Act: -0.1700
Data Index: 5237233 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.0647. Min Act: -0.1700
Data Index: 109306 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.0335. Min Act: -0.1700
Data Index: 7115014 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.0647. Min Act: -0.1700
Data Index: 4237842 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4398. Min Range: -4.4398
Max Act: 4.0647. Min Act: -0.1700
Data Index: 7422947 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19