Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1714 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.6341. Min Act: -0.1700
Data Index: 3605458 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.4154. Min Act: -0.1700
Data Index: 8528073 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.3216. Min Act: -0.1700
Data Index: 1086507 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.2904. Min Act: -0.1700
Data Index: 1683309 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.2591. Min Act: -0.1700
Data Index: 3729919 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.2591. Min Act: -0.1700
Data Index: 5788302 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.2279. Min Act: -0.1700
Data Index: 1434756 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.2279. Min Act: -0.1700
Data Index: 3544823 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.2279. Min Act: -0.1700
Data Index: 5081210 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.2279. Min Act: -0.1700
Data Index: 164428 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.2279. Min Act: -0.1700
Data Index: 4123839 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1654. Min Act: -0.1700
Data Index: 1682954 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1966. Min Act: -0.1700
Data Index: 7079049 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1966. Min Act: -0.1700
Data Index: 6645160 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1341. Min Act: -0.1700
Data Index: 3478687 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1654. Min Act: -0.1700
Data Index: 8071486 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1654. Min Act: -0.1700
Data Index: 3901901 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1341. Min Act: -0.1700
Data Index: 3497274 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1341. Min Act: -0.1700
Data Index: 1899440 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6341. Min Range: -5.6341
Max Act: 5.1654. Min Act: -0.1700
Data Index: 4476519 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19