Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1100 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8446. Min Act: -0.1700
Data Index: 6621583 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8446. Min Act: -0.1700
Data Index: 6165897 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8287. Min Act: -0.1700
Data Index: 4557997 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8446. Min Act: -0.1700
Data Index: 6312558 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8287. Min Act: -0.1700
Data Index: 8537263 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8128. Min Act: -0.1700
Data Index: 2715423 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8287. Min Act: -0.1700
Data Index: 476680 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8287. Min Act: -0.1700
Data Index: 1743156 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8287. Min Act: -0.1700
Data Index: 8144136 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.7969. Min Act: -0.1700
Data Index: 8333541 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8128. Min Act: -0.1700
Data Index: 5920798 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8128. Min Act: -0.1700
Data Index: 5764522 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.8128. Min Act: -0.1700
Data Index: 4792543 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.7969. Min Act: -0.1700
Data Index: 8537276 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.7969. Min Act: -0.1700
Data Index: 3555637 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.7809. Min Act: -0.1700
Data Index: 6770362 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.7809. Min Act: -0.1700
Data Index: 5467184 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.7809. Min Act: -0.1700
Data Index: 1133044 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.7809. Min Act: -0.1700
Data Index: 4220607 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8446. Min Range: -2.8446
Max Act: 2.7809. Min Act: -0.1700
Data Index: 5541504 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19