Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2598. Min Range: -8.2598
Max Act: 8.2598. Min Act: -0.1700
Data Index: 7013962 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2598. Min Range: -8.2598
Max Act: 8.0098. Min Act: -0.1700
Data Index: 8308154 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2598. Min Range: -8.2598
Max Act: 8.0098. Min Act: -0.1700
Data Index: 7670057 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2598. Min Range: -8.2598
Max Act: 8.0098. Min Act: -0.1700
Data Index: 3045850 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.9473. Min Act: -0.1700
Data Index: 667512 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.9473. Min Act: -0.1700
Data Index: 4312517 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2598. Min Range: -8.2598
Max Act: 8.0098. Min Act: -0.1700
Data Index: 3760371 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.8848. Min Act: -0.1700
Data Index: 1404567 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.8848. Min Act: -0.1699
Data Index: 3825813 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.8848. Min Act: -0.1700
Data Index: 3005514 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.8848. Min Act: -0.1700
Data Index: 393358 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.7598. Min Act: -0.1700
Data Index: 7306022 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.8223. Min Act: -0.1700
Data Index: 625316 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.7598. Min Act: -0.1700
Data Index: 37765 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.7598. Min Act: -0.1700
Data Index: 134438 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.7598. Min Act: -0.1700
Data Index: 5371096 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.7598. Min Act: -0.1700
Data Index: 5851948 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.7598. Min Act: -0.1700
Data Index: 6031932 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.7598. Min Act: -0.1700
Data Index: 4535838 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2598. Min Range: -8.2598
Max Act: 7.7598. Min Act: -0.1700
Data Index: 7228193 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19