Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.5252. Min Act: -0.1700
Data Index: 1035850 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.4313. Min Act: -0.1700
Data Index: 8137514 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.4156. Min Act: -0.1700
Data Index: 263682 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.3372. Min Act: -0.1700
Data Index: 1569603 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.2901. Min Act: -0.1700
Data Index: 4529164 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.2587. Min Act: -0.1700
Data Index: 611778 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.2272. Min Act: -0.1700
Data Index: 290871 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.2272. Min Act: -0.1700
Data Index: 1567966 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.2115. Min Act: -0.1700
Data Index: 6647585 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.2272. Min Act: -0.1700
Data Index: 3396790 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.2115. Min Act: -0.1700
Data Index: 538215 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1801. Min Act: -0.1700
Data Index: 7829871 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1801. Min Act: -0.1700
Data Index: 4077356 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1643. Min Act: -0.1700
Data Index: 8117348 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1486. Min Act: -0.1700
Data Index: 3865508 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1328. Min Act: -0.1700
Data Index: 2985812 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1486. Min Act: -0.1700
Data Index: 3869517 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1328. Min Act: -0.1700
Data Index: 367357 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1328. Min Act: -0.1700
Data Index: 8766429 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5252. Min Range: -3.5252
Max Act: 3.1486. Min Act: -0.1700
Data Index: 4762454 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19