Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4688 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.6368. Min Act: -0.1700
Data Index: 8539463 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.5743. Min Act: -0.1700
Data Index: 1498449 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.5743. Min Act: -0.1700
Data Index: 7506336 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.5743. Min Act: -0.1700
Data Index: 95578 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.5743. Min Act: -0.1700
Data Index: 2740276 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.5430. Min Act: -0.1700
Data Index: 6764050 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.5117. Min Act: -0.1700
Data Index: 2157036 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.5117. Min Act: -0.1700
Data Index: 6923980 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4492. Min Act: -0.1700
Data Index: 6400870 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4492. Min Act: -0.1700
Data Index: 7305204 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4492. Min Act: -0.1700
Data Index: 4123248 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4492. Min Act: -0.1700
Data Index: 367098 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4492. Min Act: -0.1700
Data Index: 4465972 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4492. Min Act: -0.1700
Data Index: 5854071 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4180. Min Act: -0.1700
Data Index: 7014158 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4180. Min Act: -0.1700
Data Index: 7213455 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.3867. Min Act: -0.1700
Data Index: 4908270 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4180. Min Act: -0.1700
Data Index: 6530940 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4180. Min Act: -0.1700
Data Index: 5656381 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6368. Min Range: -4.6368
Max Act: 4.4180. Min Act: -0.1700
Data Index: 691253 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19