Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6368 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3182. Min Range: -6.3182
Max Act: 6.3182. Min Act: -0.1700
Data Index: 4847712 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3182. Min Range: -6.3182
Max Act: 6.3182. Min Act: -0.1700
Data Index: 7733220 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3182. Min Range: -6.3182
Max Act: 6.0370. Min Act: -0.1700
Data Index: 2828218 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.9120. Min Act: -0.1700
Data Index: 7244194 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.9120. Min Act: -0.1700
Data Index: 2331493 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.9120. Min Act: -0.1700
Data Index: 4631132 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.8182. Min Act: -0.1700
Data Index: 647409 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.8182. Min Act: -0.1700
Data Index: 8478790 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.8182. Min Act: -0.1700
Data Index: 4631117 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.8182. Min Act: -0.1700
Data Index: 5018710 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.7870. Min Act: -0.1700
Data Index: 5200791 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.7557. Min Act: -0.1700
Data Index: 5124193 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.7557. Min Act: -0.1700
Data Index: 2505089 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.7245. Min Act: -0.1700
Data Index: 7365348 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.6932. Min Act: -0.1700
Data Index: 2947000 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.6932. Min Act: -0.1700
Data Index: 7020513 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.6620. Min Act: -0.1700
Data Index: 450788 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.6307. Min Act: -0.1700
Data Index: 1586239 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.6620. Min Act: -0.1700
Data Index: 4876920 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3182. Min Range: -6.3182
Max Act: 5.5995. Min Act: -0.1700
Data Index: 6491343 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19