Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3181. Min Range: -6.3181
Max Act: 6.3181. Min Act: -0.1700
Data Index: 8368095 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3181. Min Range: -6.3181
Max Act: 6.1619. Min Act: -0.1700
Data Index: 8525581 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3181. Min Range: -6.3181
Max Act: 6.0681. Min Act: -0.1700
Data Index: 3914628 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3181. Min Range: -6.3181
Max Act: 6.0056. Min Act: -0.1700
Data Index: 5507038 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3181. Min Range: -6.3181
Max Act: 6.0056. Min Act: -0.1700
Data Index: 7105151 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.9744. Min Act: -0.1700
Data Index: 8657780 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.9119. Min Act: -0.1700
Data Index: 5943469 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.9119. Min Act: -0.1700
Data Index: 324420 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.9431. Min Act: -0.1700
Data Index: 6637276 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.9119. Min Act: -0.1700
Data Index: 8351420 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.9119. Min Act: -0.1700
Data Index: 1693664 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8494. Min Act: -0.1700
Data Index: 6073779 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8494. Min Act: -0.1700
Data Index: 2752309 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8494. Min Act: -0.1700
Data Index: 6540171 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8181. Min Act: -0.1700
Data Index: 4975607 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8181. Min Act: -0.1700
Data Index: 2211223 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8181. Min Act: -0.1700
Data Index: 8419320 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8181. Min Act: -0.1700
Data Index: 4273576 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8181. Min Act: -0.1700
Data Index: 8832587 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3181. Min Range: -6.3181
Max Act: 5.8181. Min Act: -0.1700
Data Index: 2394645 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19