Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 921 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.6387. Min Act: -0.1700
Data Index: 5103316 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.6231. Min Act: -0.1700
Data Index: 7493291 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.5292. Min Act: -0.1700
Data Index: 4774187 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.5292. Min Act: -0.1700
Data Index: 7963196 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.5292. Min Act: -0.1700
Data Index: 4423096 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4979. Min Act: -0.1700
Data Index: 1477023 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4979. Min Act: -0.1700
Data Index: 5807694 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4979. Min Act: -0.1700
Data Index: 3291186 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4822. Min Act: -0.1700
Data Index: 2179817 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4979. Min Act: -0.1700
Data Index: 7963195 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4979. Min Act: -0.1700
Data Index: 6867785 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4665. Min Act: -0.1700
Data Index: 2884014 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4665. Min Act: -0.1700
Data Index: 966612 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4979. Min Act: -0.1700
Data Index: 2797783 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4665. Min Act: -0.1700
Data Index: 66871 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4509. Min Act: -0.1700
Data Index: 6552490 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4509. Min Act: -0.1700
Data Index: 7381547 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4352. Min Act: -0.1700
Data Index: 7695226 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4352. Min Act: -0.1700
Data Index: 1223315 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6387. Min Range: -3.6387
Max Act: 3.4352. Min Act: -0.1700
Data Index: 6483276 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19