Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1820. Min Range: -6.1820
Max Act: 6.1820. Min Act: -0.1700
Data Index: 3625786 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1820. Min Range: -6.1820
Max Act: 6.0257. Min Act: -0.1700
Data Index: 7129642 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.9320. Min Act: -0.1700
Data Index: 7746703 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.8382. Min Act: -0.1700
Data Index: 6403360 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.8070. Min Act: -0.1700
Data Index: 3490567 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.8382. Min Act: -0.1700
Data Index: 207403 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.7757. Min Act: -0.1700
Data Index: 5833418 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.7132. Min Act: -0.1700
Data Index: 1650983 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.7132. Min Act: -0.1700
Data Index: 1685 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.7132. Min Act: -0.1700
Data Index: 2576903 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.7132. Min Act: -0.1700
Data Index: 7765452 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.6820. Min Act: -0.1700
Data Index: 2562101 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.6507. Min Act: -0.1700
Data Index: 5564064 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.6507. Min Act: -0.1700
Data Index: 4120923 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.6195. Min Act: -0.1700
Data Index: 4012584 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.5882. Min Act: -0.1700
Data Index: 6419474 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.5882. Min Act: -0.1700
Data Index: 708267 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.5257. Min Act: -0.1700
Data Index: 4966495 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.5570. Min Act: -0.1700
Data Index: 2891176 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1820. Min Range: -6.1820
Max Act: 5.5257. Min Act: -0.1700
Data Index: 3132134 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19