Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.2177. Min Act: -0.1700
Data Index: 5131661 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.2177. Min Act: -0.1700
Data Index: 3793592 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.0927. Min Act: -0.1700
Data Index: 6847514 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.0927. Min Act: -0.1700
Data Index: 8286016 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.0615. Min Act: -0.1700
Data Index: 88524 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.0302. Min Act: -0.1700
Data Index: 1843030 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.0302. Min Act: -0.1700
Data Index: 6810266 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.0302. Min Act: -0.1700
Data Index: 2514660 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.0302. Min Act: -0.1695
Data Index: 8007579 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2177. Min Range: -6.2177
Max Act: 6.0302. Min Act: -0.1700
Data Index: 3628247 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9677. Min Act: -0.1700
Data Index: 401441 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9990. Min Act: -0.1700
Data Index: 3891918 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9365. Min Act: -0.1700
Data Index: 2932271 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9677. Min Act: -0.1695
Data Index: 5647445 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9677. Min Act: -0.1700
Data Index: 7471349 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9677. Min Act: -0.1700
Data Index: 5635467 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9677. Min Act: -0.1700
Data Index: 1541558 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9677. Min Act: -0.1700
Data Index: 6223433 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9677. Min Act: -0.1700
Data Index: 645846 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2177. Min Range: -6.2177
Max Act: 5.9677. Min Act: -0.1700
Data Index: 7268608 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19