Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 131 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.9382. Min Act: -0.1700
Data Index: 8321940 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.9382. Min Act: -0.1700
Data Index: 5270003 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.6882. Min Act: -0.1700
Data Index: 2855665 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.5007. Min Act: -0.1700
Data Index: 2109219 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.5007. Min Act: -0.1700
Data Index: 3554587 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.4382. Min Act: -0.1700
Data Index: 8088349 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.3757. Min Act: -0.1700
Data Index: 7405053 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.4382. Min Act: -0.1700
Data Index: 4767631 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.3132. Min Act: -0.1700
Data Index: 3936754 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.3757. Min Act: -0.1700
Data Index: 1052332 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.3132. Min Act: -0.1700
Data Index: 6689092 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.2507. Min Act: -0.1700
Data Index: 5152155 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.2507. Min Act: -0.1700
Data Index: 5167135 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.1882. Min Act: -0.1700
Data Index: 1834035 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.1882. Min Act: -0.1700
Data Index: 8688840 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.1882. Min Act: -0.1700
Data Index: 7976676 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.1569. Min Act: -0.1700
Data Index: 7412196 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.1569. Min Act: -0.1700
Data Index: 100459 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.1257. Min Act: -0.1700
Data Index: 8120786 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9382. Min Range: -8.9382
Max Act: 8.1569. Min Act: -0.1700
Data Index: 5056950 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19