Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2858 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5481. Min Act: -0.1700
Data Index: 6998740 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5168. Min Act: -0.1700
Data Index: 504095 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5168. Min Act: -0.1700
Data Index: 8752459 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5481. Min Act: -0.1700
Data Index: 7610243 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5168. Min Act: -0.1700
Data Index: 3703755 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5168. Min Act: -0.1700
Data Index: 596537 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5168. Min Act: -0.1700
Data Index: 397865 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5168. Min Act: -0.1700
Data Index: 7389624 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5168. Min Act: -0.1700
Data Index: 4675384 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.5168. Min Act: -0.1700
Data Index: 4675380 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4856. Min Act: -0.1700
Data Index: 583176 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4856. Min Act: -0.1700
Data Index: 8494225 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4856. Min Act: -0.1700
Data Index: 8781988 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4856. Min Act: -0.1700
Data Index: 1691345 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4856. Min Act: -0.1700
Data Index: 1106299 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4856. Min Act: -0.1700
Data Index: 6044888 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4543. Min Act: -0.1700
Data Index: 6324099 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4543. Min Act: -0.1700
Data Index: 1739156 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.4543. Min Act: -0.1700
Data Index: 6822585 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5481. Min Range: -4.5481
Max Act: 4.3918. Min Act: -0.1700
Data Index: 1891857 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19