Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.6399. Min Act: -0.1700
Data Index: 7501148 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.4837. Min Act: -0.1700
Data Index: 5530293 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.4212. Min Act: -0.1700
Data Index: 917911 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.4212. Min Act: -0.1700
Data Index: 5550965 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.3587. Min Act: -0.1700
Data Index: 4634671 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.2649. Min Act: -0.1700
Data Index: 2489872 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.2649. Min Act: -0.1700
Data Index: 8265367 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.2024. Min Act: -0.1700
Data Index: 7465779 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.2337. Min Act: -0.1700
Data Index: 5044026 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.2024. Min Act: -0.1700
Data Index: 8743576 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1712. Min Act: -0.1700
Data Index: 1479135 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1399. Min Act: -0.1700
Data Index: 2736149 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1399. Min Act: -0.1700
Data Index: 2620955 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1087. Min Act: -0.1700
Data Index: 7066342 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1399. Min Act: -0.1700
Data Index: 1205131 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1399. Min Act: -0.1700
Data Index: 877172 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1087. Min Act: -0.1700
Data Index: 2338726 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1087. Min Act: -0.1700
Data Index: 4676287 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1087. Min Act: -0.1700
Data Index: 4695400 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6399. Min Range: -6.6399
Max Act: 6.1087. Min Act: -0.1700
Data Index: 389239 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19