Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.6353. Min Act: -0.1700
Data Index: 1817489 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.4790. Min Act: -0.1700
Data Index: 3917684 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.4478. Min Act: -0.1700
Data Index: 3463259 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.4165. Min Act: -0.1700
Data Index: 106788 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.3853. Min Act: -0.1700
Data Index: 8145855 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.3228. Min Act: -0.1700
Data Index: 148027 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.3540. Min Act: -0.1700
Data Index: 4431768 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.2915. Min Act: -0.1700
Data Index: 7603281 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.2603. Min Act: -0.1700
Data Index: 3521899 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.2603. Min Act: -0.1700
Data Index: 223921 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.2603. Min Act: -0.1700
Data Index: 147229 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.2290. Min Act: -0.1700
Data Index: 6905098 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.2290. Min Act: -0.1700
Data Index: 5845050 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.1978. Min Act: -0.1700
Data Index: 7377151 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.1978. Min Act: -0.1700
Data Index: 2181040 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.1978. Min Act: -0.1700
Data Index: 265743 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.1978. Min Act: -0.1700
Data Index: 5458584 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.1665. Min Act: -0.1700
Data Index: 5834801 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.1665. Min Act: -0.1700
Data Index: 2052747 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6353. Min Range: -5.6353
Max Act: 5.1665. Min Act: -0.1700
Data Index: 1770630 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19