Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3214. Min Range: -7.3214
Max Act: 7.3214. Min Act: -0.1700
Data Index: 3233383 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3214. Min Range: -7.3214
Max Act: 7.0402. Min Act: -0.1700
Data Index: 2936410 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3214. Min Range: -7.3214
Max Act: 7.0402. Min Act: -0.1700
Data Index: 6911067 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3214. Min Range: -7.3214
Max Act: 7.0402. Min Act: -0.1700
Data Index: 4003362 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.7589. Min Act: -0.1700
Data Index: 5730116 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.6339. Min Act: -0.1700
Data Index: 1243018 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.6027. Min Act: -0.1700
Data Index: 127888 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.5402. Min Act: -0.1700
Data Index: 5172951 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.5089. Min Act: -0.1700
Data Index: 2170015 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.5089. Min Act: -0.1700
Data Index: 430731 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.4777. Min Act: -0.1700
Data Index: 8564606 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.5089. Min Act: -0.1700
Data Index: 7888767 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.4152. Min Act: -0.1700
Data Index: 639129 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.4152. Min Act: -0.1700
Data Index: 6574399 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.4152. Min Act: -0.1700
Data Index: 504995 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.4152. Min Act: -0.1700
Data Index: 1937684 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.4464. Min Act: -0.1700
Data Index: 8810638 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.3527. Min Act: -0.1700
Data Index: 4015097 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.3214. Min Act: -0.1700
Data Index: 4865212 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3214. Min Range: -7.3214
Max Act: 6.2902. Min Act: -0.1700
Data Index: 2784761 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19