Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1230. Min Range: -4.1230
Max Act: 4.1230. Min Act: -0.1700
Data Index: 5779657 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1230. Min Range: -4.1230
Max Act: 4.0918. Min Act: -0.1700
Data Index: 3271472 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1230. Min Range: -4.1230
Max Act: 4.0605. Min Act: -0.1700
Data Index: 5868301 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1230. Min Range: -4.1230
Max Act: 4.0293. Min Act: -0.1700
Data Index: 3555774 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.9980. Min Act: -0.1700
Data Index: 326054 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.9980. Min Act: -0.1700
Data Index: 1513567 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.9667. Min Act: -0.1700
Data Index: 5206185 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.9667. Min Act: -0.1700
Data Index: 8436648 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8730. Min Act: -0.1700
Data Index: 5023572 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.9355. Min Act: -0.1700
Data Index: 1939353 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8730. Min Act: -0.1700
Data Index: 5382454 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.9355. Min Act: -0.1700
Data Index: 8270688 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8730. Min Act: -0.1700
Data Index: 6855982 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8730. Min Act: -0.1700
Data Index: 6263430 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8730. Min Act: -0.1700
Data Index: 6263431 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8730. Min Act: -0.1700
Data Index: 5672705 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8730. Min Act: -0.1700
Data Index: 8552855 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8730. Min Act: -0.1700
Data Index: 326055 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8417. Min Act: -0.1700
Data Index: 6115087 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1230. Min Range: -4.1230
Max Act: 3.8417. Min Act: -0.1700
Data Index: 7278020 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19