Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6280 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2231. Min Range: -8.2231
Max Act: 8.2231. Min Act: -0.1700
Data Index: 3883642 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.8481. Min Act: -0.1700
Data Index: 4148170 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.7231. Min Act: -0.1700
Data Index: 2940906 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.5356. Min Act: -0.1700
Data Index: 3034285 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.4731. Min Act: -0.1700
Data Index: 2426636 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.4106. Min Act: -0.1700
Data Index: 8466113 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.3794. Min Act: -0.1700
Data Index: 1551723 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.3794. Min Act: -0.1700
Data Index: 8264034 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.3481. Min Act: -0.1700
Data Index: 777133 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.3481. Min Act: -0.1700
Data Index: 6372836 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.3169. Min Act: -0.1700
Data Index: 2902965 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.3169. Min Act: -0.1700
Data Index: 3978436 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.2544. Min Act: -0.1700
Data Index: 6469825 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.2544. Min Act: -0.1700
Data Index: 2682161 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.1919. Min Act: -0.1700
Data Index: 1878995 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.1919. Min Act: -0.1700
Data Index: 1407902 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.1919. Min Act: -0.1700
Data Index: 4582424 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.1606. Min Act: -0.1700
Data Index: 4162969 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.1606. Min Act: -0.1700
Data Index: 5760446 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2231. Min Range: -8.2231
Max Act: 7.1606. Min Act: -0.1700
Data Index: 378138 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19