Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4446 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6451. Min Range: -6.6451
Max Act: 6.6451. Min Act: -0.1700
Data Index: 952811 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6451. Min Range: -6.6451
Max Act: 6.3013. Min Act: -0.1700
Data Index: 4425067 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6451. Min Range: -6.6451
Max Act: 6.3013. Min Act: -0.1700
Data Index: 7991882 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6451. Min Range: -6.6451
Max Act: 6.0826. Min Act: -0.1700
Data Index: 1343160 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6451. Min Range: -6.6451
Max Act: 6.0826. Min Act: -0.1700
Data Index: 8442541 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6451. Min Range: -6.6451
Max Act: 6.0826. Min Act: -0.1700
Data Index: 725941 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6451. Min Range: -6.6451
Max Act: 6.0201. Min Act: -0.1700
Data Index: 3892286 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.9888. Min Act: -0.1700
Data Index: 3196027 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.9576. Min Act: -0.1700
Data Index: 1787670 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.9888. Min Act: -0.1700
Data Index: 388574 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.9263. Min Act: -0.1700
Data Index: 1555643 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8951. Min Act: -0.1700
Data Index: 932526 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8951. Min Act: -0.1700
Data Index: 6017247 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8951. Min Act: -0.1700
Data Index: 4974436 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8638. Min Act: -0.1700
Data Index: 4300329 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8326. Min Act: -0.1700
Data Index: 6983611 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8638. Min Act: -0.1700
Data Index: 1379235 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8326. Min Act: -0.1700
Data Index: 5543622 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8326. Min Act: -0.1700
Data Index: 8359411 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6451. Min Range: -6.6451
Max Act: 5.8326. Min Act: -0.1700
Data Index: 6231249 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19