Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5764 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4630. Min Range: -7.4630
Max Act: 7.4630. Min Act: -0.1700
Data Index: 4583689 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4630. Min Range: -7.4630
Max Act: 7.2130. Min Act: -0.1700
Data Index: 4820875 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4630. Min Range: -7.4630
Max Act: 7.1505. Min Act: -0.1700
Data Index: 4168169 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4630. Min Range: -7.4630
Max Act: 7.1193. Min Act: -0.1700
Data Index: 5560552 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4630. Min Range: -7.4630
Max Act: 7.0880. Min Act: -0.1700
Data Index: 917255 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4630. Min Range: -7.4630
Max Act: 7.0880. Min Act: -0.1700
Data Index: 1812219 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9318. Min Act: -0.1700
Data Index: 6725116 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9630. Min Act: -0.1700
Data Index: 6721715 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9943. Min Act: -0.1700
Data Index: 7088207 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9630. Min Act: -0.1700
Data Index: 6323287 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9318. Min Act: -0.1700
Data Index: 6953121 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9318. Min Act: -0.1700
Data Index: 8488773 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9318. Min Act: -0.1700
Data Index: 8117266 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9005. Min Act: -0.1700
Data Index: 8021234 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.9005. Min Act: -0.1700
Data Index: 4489605 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.8693. Min Act: -0.1700
Data Index: 4118345 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.8693. Min Act: -0.1700
Data Index: 7866435 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.8693. Min Act: -0.1700
Data Index: 4364445 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.8068. Min Act: -0.1700
Data Index: 2770859 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4630. Min Range: -7.4630
Max Act: 6.7755. Min Act: -0.1700
Data Index: 5223166 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19