Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 325 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.2849. Min Act: -0.1700
Data Index: 50932 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.2536. Min Act: -0.1700
Data Index: 3877774 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.1911. Min Act: -0.1700
Data Index: 807165 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.1286. Min Act: -0.1700
Data Index: 6345637 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.1286. Min Act: -0.1700
Data Index: 1120304 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.1286. Min Act: -0.1700
Data Index: 8027905 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.1286. Min Act: -0.1700
Data Index: 8331724 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0974. Min Act: -0.1700
Data Index: 1157850 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0974. Min Act: -0.1700
Data Index: 1391151 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0974. Min Act: -0.1700
Data Index: 5921301 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0661. Min Act: -0.1700
Data Index: 6672321 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0661. Min Act: -0.1700
Data Index: 5957483 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0349. Min Act: -0.1700
Data Index: 3112841 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0036. Min Act: -0.1700
Data Index: 6015829 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0349. Min Act: -0.1700
Data Index: 8396266 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0036. Min Act: -0.1700
Data Index: 4512147 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0036. Min Act: -0.1700
Data Index: 3763999 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0036. Min Act: -0.1700
Data Index: 2000029 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0036. Min Act: -0.1700
Data Index: 4946856 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2849. Min Range: -4.2849
Max Act: 4.0036. Min Act: -0.1700
Data Index: 3513130 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19