Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3461 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.4398. Min Act: -0.1700
Data Index: 3369410 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.3773. Min Act: -0.1700
Data Index: 2699279 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.3461. Min Act: -0.1700
Data Index: 3208741 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.2836. Min Act: -0.1700
Data Index: 4025368 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.3148. Min Act: -0.1700
Data Index: 5996422 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.2523. Min Act: -0.1700
Data Index: 8404339 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.2523. Min Act: -0.1700
Data Index: 5577075 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.1898. Min Act: -0.1700
Data Index: 7770899 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.1586. Min Act: -0.1700
Data Index: 5527826 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.1586. Min Act: -0.1700
Data Index: 6242512 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0961. Min Act: -0.1700
Data Index: 3208740 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0961. Min Act: -0.1700
Data Index: 3484815 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0961. Min Act: -0.1700
Data Index: 8274310 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0336. Min Act: -0.1700
Data Index: 686031 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0648. Min Act: -0.1700
Data Index: 67513 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0961. Min Act: -0.1700
Data Index: 6373428 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0336. Min Act: -0.1700
Data Index: 5421441 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0336. Min Act: -0.1700
Data Index: 7771079 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0336. Min Act: -0.1700
Data Index: 3809912 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4398. Min Range: -5.4398
Max Act: 5.0336. Min Act: -0.1700
Data Index: 2626391 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19