Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3192. Min Range: -6.3192
Max Act: 6.3192. Min Act: -0.1700
Data Index: 6372254 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3192. Min Range: -6.3192
Max Act: 6.1629. Min Act: -0.1700
Data Index: 4153337 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3192. Min Range: -6.3192
Max Act: 6.1317. Min Act: -0.1700
Data Index: 2752956 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3192. Min Range: -6.3192
Max Act: 6.1004. Min Act: -0.1700
Data Index: 8488282 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3192. Min Range: -6.3192
Max Act: 6.0379. Min Act: -0.1700
Data Index: 2398505 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.9754. Min Act: -0.1700
Data Index: 362337 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3192. Min Range: -6.3192
Max Act: 6.0067. Min Act: -0.1700
Data Index: 1800690 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3192. Min Range: -6.3192
Max Act: 6.0067. Min Act: -0.1700
Data Index: 7702021 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.9754. Min Act: -0.1700
Data Index: 5610045 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.9129. Min Act: -0.1700
Data Index: 947760 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.8817. Min Act: -0.1700
Data Index: 1750345 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.8817. Min Act: -0.1700
Data Index: 7608226 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.8504. Min Act: -0.1700
Data Index: 2245139 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.8504. Min Act: -0.1700
Data Index: 3258864 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.8504. Min Act: -0.1700
Data Index: 2160575 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.8504. Min Act: -0.1700
Data Index: 7995587 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.8192. Min Act: -0.1700
Data Index: 1072805 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.7879. Min Act: -0.1700
Data Index: 5187374 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.7567. Min Act: -0.1700
Data Index: 3241640 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3192. Min Range: -6.3192
Max Act: 5.7567. Min Act: -0.1700
Data Index: 1253304 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19