Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1096 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.9294. Min Act: -0.1700
Data Index: 2894149 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.8669. Min Act: -0.1700
Data Index: 3597614 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.8357. Min Act: -0.1700
Data Index: 6930878 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.8357. Min Act: -0.1700
Data Index: 1747956 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.8357. Min Act: -0.1700
Data Index: 2375538 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.8357. Min Act: -0.1700
Data Index: 5105784 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.8044. Min Act: -0.1700
Data Index: 843058 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7419. Min Act: -0.1700
Data Index: 5537031 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7732. Min Act: -0.1700
Data Index: 3185172 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7419. Min Act: -0.1700
Data Index: 6502827 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7419. Min Act: -0.1700
Data Index: 4378799 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7419. Min Act: -0.1700
Data Index: 4597320 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7419. Min Act: -0.1700
Data Index: 595037 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2259470 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7107. Min Act: -0.1700
Data Index: 6240515 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7107. Min Act: -0.1700
Data Index: 652290 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7107. Min Act: -0.1700
Data Index: 141441 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.7107. Min Act: -0.1700
Data Index: 1867529 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.6794. Min Act: -0.1700
Data Index: 6124988 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9294. Min Range: -4.9294
Max Act: 4.6794. Min Act: -0.1700
Data Index: 1136084 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19