Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6202 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.6134. Min Act: -0.1700
Data Index: 4761835 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.5509. Min Act: -0.1700
Data Index: 3038556 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.5196. Min Act: -0.1700
Data Index: 7695379 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4884. Min Act: -0.1700
Data Index: 5969122 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.4259. Min Act: -0.1700
Data Index: 5826907 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3634. Min Act: -0.1700
Data Index: 943420 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3321. Min Act: -0.1700
Data Index: 5472770 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3009. Min Act: -0.1700
Data Index: 1984194 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.3009. Min Act: -0.1700
Data Index: 8563175 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.2696. Min Act: -0.1700
Data Index: 3226509 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.2384. Min Act: -0.1700
Data Index: 914340 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.2384. Min Act: -0.1700
Data Index: 6842844 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.2384. Min Act: -0.1700
Data Index: 8586869 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.2384. Min Act: -0.1700
Data Index: 4275248 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.1759. Min Act: -0.1700
Data Index: 3672290 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.2071. Min Act: -0.1700
Data Index: 476294 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.2071. Min Act: -0.1700
Data Index: 3679474 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.1759. Min Act: -0.1700
Data Index: 5474317 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.1759. Min Act: -0.1700
Data Index: 653895 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6134. Min Range: -6.6134
Max Act: 6.1759. Min Act: -0.1700
Data Index: 8010992 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19