Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.8580. Min Act: -0.1700
Data Index: 6096694 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.6705. Min Act: -0.1700
Data Index: 249044 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.6705. Min Act: -0.1700
Data Index: 812595 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.6392. Min Act: -0.1699
Data Index: 4020823 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.6392. Min Act: -0.1700
Data Index: 4020822 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.5767. Min Act: -0.1700
Data Index: 7422877 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.5767. Min Act: -0.1700
Data Index: 6528110 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.5142. Min Act: -0.1700
Data Index: 8129246 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4830. Min Act: -0.1696
Data Index: 4020824 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4830. Min Act: -0.1700
Data Index: 170234 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4830. Min Act: -0.1700
Data Index: 819768 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4517. Min Act: -0.1700
Data Index: 4762178 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4517. Min Act: -0.1700
Data Index: 1608915 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4517. Min Act: -0.1700
Data Index: 6585124 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4517. Min Act: -0.1700
Data Index: 6132233 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4205. Min Act: -0.1700
Data Index: 974931 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.4205. Min Act: -0.1700
Data Index: 3666211 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.3892. Min Act: -0.1700
Data Index: 312650 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.3892. Min Act: -0.1700
Data Index: 5524149 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8580. Min Range: -4.8580
Max Act: 4.3892. Min Act: -0.1700
Data Index: 6031805 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19