Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6994. Min Range: -8.6994
Max Act: 8.6994. Min Act: -0.1700
Data Index: 8649815 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6994. Min Range: -8.6994
Max Act: 8.5119. Min Act: -0.1700
Data Index: 2915514 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6994. Min Range: -8.6994
Max Act: 8.3869. Min Act: -0.1700
Data Index: 2676769 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6994. Min Range: -8.6994
Max Act: 8.1369. Min Act: -0.1700
Data Index: 5639139 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6994. Min Range: -8.6994
Max Act: 8.0119. Min Act: -0.1700
Data Index: 7948144 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.9494. Min Act: -0.1700
Data Index: 2097460 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.8869. Min Act: -0.1700
Data Index: 4581584 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.8244. Min Act: -0.1700
Data Index: 8525574 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.7619. Min Act: -0.1700
Data Index: 4138160 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.7619. Min Act: -0.1700
Data Index: 4621425 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.6994. Min Act: -0.1700
Data Index: 5549734 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.6994. Min Act: -0.1700
Data Index: 4679223 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.6369. Min Act: -0.1700
Data Index: 499444 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.6369. Min Act: -0.1700
Data Index: 4774192 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.6994. Min Act: -0.1700
Data Index: 2488552 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.6369. Min Act: -0.1700
Data Index: 1484191 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.6369. Min Act: -0.1700
Data Index: 3752928 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.5744. Min Act: -0.1700
Data Index: 6861358 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.5744. Min Act: -0.1700
Data Index: 2837636 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6994. Min Range: -8.6994
Max Act: 7.5744. Min Act: -0.1700
Data Index: 4265721 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19