Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 594 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.5268. Min Act: -0.1700
Data Index: 353661 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.5268. Min Act: -0.1700
Data Index: 6166070 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.4955. Min Act: -0.1700
Data Index: 3281626 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.4330. Min Act: -0.1700
Data Index: 1649464 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.4330. Min Act: -0.1700
Data Index: 4098200 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.4330. Min Act: -0.1700
Data Index: 4098201 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.4330. Min Act: -0.1700
Data Index: 5415769 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.4018. Min Act: -0.1700
Data Index: 5974280 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3705. Min Act: -0.1700
Data Index: 8631209 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3393. Min Act: -0.1700
Data Index: 8161146 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3080. Min Act: -0.1700
Data Index: 3736231 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3080. Min Act: -0.1700
Data Index: 3281628 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.3080. Min Act: -0.1700
Data Index: 5709441 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.2143. Min Act: -0.1700
Data Index: 6640538 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.2455. Min Act: -0.1700
Data Index: 1006869 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.2143. Min Act: -0.1700
Data Index: 4798463 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.2143. Min Act: -0.1700
Data Index: 4397430 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.2143. Min Act: -0.1700
Data Index: 5360802 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.2143. Min Act: -0.1700
Data Index: 4312175 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5268. Min Range: -6.5268
Max Act: 6.1830. Min Act: -0.1700
Data Index: 2729717 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19