Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6427. Min Range: -7.6427
Max Act: 7.6427. Min Act: -0.1700
Data Index: 7912987 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6427. Min Range: -7.6427
Max Act: 7.3302. Min Act: -0.1700
Data Index: 678032 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6427. Min Range: -7.6427
Max Act: 7.2364. Min Act: -0.1700
Data Index: 7163285 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6427. Min Range: -7.6427
Max Act: 7.2052. Min Act: -0.1700
Data Index: 1120550 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6427. Min Range: -7.6427
Max Act: 7.0802. Min Act: -0.1700
Data Index: 2281522 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6427. Min Range: -7.6427
Max Act: 7.0489. Min Act: -0.1700
Data Index: 1712128 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6427. Min Range: -7.6427
Max Act: 7.0177. Min Act: -0.1700
Data Index: 3004627 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6427. Min Range: -7.6427
Max Act: 7.0177. Min Act: -0.1700
Data Index: 2929562 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.9864. Min Act: -0.1700
Data Index: 8384602 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.9239. Min Act: -0.1700
Data Index: 4543023 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.9239. Min Act: -0.1700
Data Index: 131664 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8927. Min Act: -0.1700
Data Index: 3462382 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8614. Min Act: -0.1700
Data Index: 1999557 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8614. Min Act: -0.1700
Data Index: 6954160 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8614. Min Act: -0.1700
Data Index: 6021302 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8302. Min Act: -0.1700
Data Index: 5052420 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8302. Min Act: -0.1700
Data Index: 1566437 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8302. Min Act: -0.1700
Data Index: 4239006 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8302. Min Act: -0.1700
Data Index: 6292411 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6427. Min Range: -7.6427
Max Act: 6.8302. Min Act: -0.1700
Data Index: 7253188 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19