Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.4382. Min Act: -0.1700
Data Index: 1506697 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.3757. Min Act: -0.1700
Data Index: 5632066 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.3444. Min Act: -0.1700
Data Index: 2949805 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.3132. Min Act: -0.1700
Data Index: 2728814 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.2507. Min Act: -0.1700
Data Index: 8472141 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.2194. Min Act: -0.1700
Data Index: 8519387 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.1569. Min Act: -0.1700
Data Index: 2597512 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.1257. Min Act: -0.1700
Data Index: 620082 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.0944. Min Act: -0.1700
Data Index: 7381138 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.1257. Min Act: -0.1700
Data Index: 5519774 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.0632. Min Act: -0.1700
Data Index: 3139965 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.0319. Min Act: -0.1700
Data Index: 2647857 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4382. Min Range: -7.4382
Max Act: 7.0007. Min Act: -0.1700
Data Index: 3139962 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4382. Min Range: -7.4382
Max Act: 6.9382. Min Act: -0.1700
Data Index: 715182 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4382. Min Range: -7.4382
Max Act: 6.9382. Min Act: -0.1700
Data Index: 8827358 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4382. Min Range: -7.4382
Max Act: 6.9069. Min Act: -0.1700
Data Index: 4405882 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4382. Min Range: -7.4382
Max Act: 6.9069. Min Act: -0.1700
Data Index: 8734342 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4382. Min Range: -7.4382
Max Act: 6.9069. Min Act: -0.1700
Data Index: 5219498 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4382. Min Range: -7.4382
Max Act: 6.8757. Min Act: -0.1700
Data Index: 6872355 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4382. Min Range: -7.4382
Max Act: 6.8757. Min Act: -0.1700
Data Index: 7896061 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19