Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6190 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5314. Min Range: -6.5314
Max Act: 6.5314. Min Act: -0.1700
Data Index: 3732416 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5314. Min Range: -6.5314
Max Act: 6.4376. Min Act: -0.1700
Data Index: 209155 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5314. Min Range: -6.5314
Max Act: 6.4689. Min Act: -0.1700
Data Index: 3478313 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5314. Min Range: -6.5314
Max Act: 6.1251. Min Act: -0.1700
Data Index: 3446268 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5314. Min Range: -6.5314
Max Act: 6.0626. Min Act: -0.1700
Data Index: 168976 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.9376. Min Act: -0.1700
Data Index: 5274598 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.9064. Min Act: -0.1700
Data Index: 284958 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.9376. Min Act: -0.1700
Data Index: 6165482 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.9064. Min Act: -0.1700
Data Index: 5159941 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.9064. Min Act: -0.1700
Data Index: 1442354 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.8751. Min Act: -0.1700
Data Index: 4896270 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.7814. Min Act: -0.1700
Data Index: 6091733 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.7814. Min Act: -0.1700
Data Index: 1024909 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.7814. Min Act: -0.1700
Data Index: 8049185 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.8126. Min Act: -0.1700
Data Index: 4530382 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.7814. Min Act: -0.1700
Data Index: 8785598 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.7814. Min Act: -0.1700
Data Index: 7825848 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.7814. Min Act: -0.1700
Data Index: 7892080 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.7814. Min Act: -0.1700
Data Index: 4620638 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5314. Min Range: -6.5314
Max Act: 5.7189. Min Act: -0.1700
Data Index: 861531 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19