Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0841. Min Range: -5.0841
Max Act: 5.0841. Min Act: -0.1700
Data Index: 8353083 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.9591. Min Act: -0.1700
Data Index: 321582 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.9591. Min Act: -0.1700
Data Index: 7566145 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.9278. Min Act: -0.1700
Data Index: 2236921 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.9278. Min Act: -0.1700
Data Index: 5928694 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.9278. Min Act: -0.1700
Data Index: 2111589 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.9278. Min Act: -0.1700
Data Index: 8475024 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8966. Min Act: -0.1700
Data Index: 4313466 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8653. Min Act: -0.1700
Data Index: 3286863 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8653. Min Act: -0.1700
Data Index: 6312134 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8341. Min Act: -0.1700
Data Index: 1188222 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8028. Min Act: -0.1700
Data Index: 6042489 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.7716. Min Act: -0.1700
Data Index: 6314558 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8028. Min Act: -0.1700
Data Index: 6762394 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8028. Min Act: -0.1700
Data Index: 258607 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8028. Min Act: -0.1700
Data Index: 4916534 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.8028. Min Act: -0.1700
Data Index: 1726231 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.7716. Min Act: -0.1700
Data Index: 403437 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.7403. Min Act: -0.1700
Data Index: 5611378 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.7403. Min Act: -0.1700
Data Index: 3051342 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19