Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2043 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5645. Min Act: -0.1700
Data Index: 4855157 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5645. Min Act: -0.1700
Data Index: 983803 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5958. Min Act: -0.1700
Data Index: 1415751 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5333. Min Act: -0.1700
Data Index: 6149177 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5333. Min Act: -0.1700
Data Index: 935566 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5020. Min Act: -0.1700
Data Index: 8758858 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5020. Min Act: -0.1700
Data Index: 2711272 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5020. Min Act: -0.1700
Data Index: 1442437 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4708. Min Act: -0.1700
Data Index: 4867958 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4708. Min Act: -0.1700
Data Index: 77440 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4395. Min Act: -0.1700
Data Index: 4536149 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4395. Min Act: -0.1700
Data Index: 4428719 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4395. Min Act: -0.1700
Data Index: 3385216 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4083. Min Act: -0.1700
Data Index: 505472 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4083. Min Act: -0.1700
Data Index: 3989318 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4083. Min Act: -0.1700
Data Index: 8103372 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4083. Min Act: -0.1700
Data Index: 6168630 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3770. Min Act: -0.1700
Data Index: 3122765 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.4083. Min Act: -0.1700
Data Index: 1493794 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3770. Min Act: -0.1700
Data Index: 6523026 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19