Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.3997. Min Act: -0.1700
Data Index: 1063236 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.4310. Min Act: -0.1700
Data Index: 6205599 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.3685. Min Act: -0.1700
Data Index: 6205598 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.3060. Min Act: -0.1700
Data Index: 7204255 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.2435. Min Act: -0.1700
Data Index: 7976457 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.1810. Min Act: -0.1700
Data Index: 2326020 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.1497. Min Act: -0.1700
Data Index: 3958239 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.1185. Min Act: -0.1700
Data Index: 8005485 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0872. Min Act: -0.1700
Data Index: 1313579 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0872. Min Act: -0.1700
Data Index: 3256720 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0872. Min Act: -0.1700
Data Index: 973331 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0560. Min Act: -0.1700
Data Index: 2604543 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0560. Min Act: -0.1700
Data Index: 2629398 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0560. Min Act: -0.1700
Data Index: 7204256 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0560. Min Act: -0.1700
Data Index: 2334717 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0560. Min Act: -0.1700
Data Index: 737840 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0247. Min Act: -0.1700
Data Index: 6920389 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4310. Min Range: -6.4310
Max Act: 6.0247. Min Act: -0.1700
Data Index: 6465164 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.9935. Min Act: -0.1700
Data Index: 5115894 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4310. Min Range: -6.4310
Max Act: 5.9622. Min Act: -0.1700
Data Index: 4190787 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19