Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.4098. Min Act: -0.1700
Data Index: 2364992 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.3785. Min Act: -0.1700
Data Index: 3935468 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.2535. Min Act: -0.1700
Data Index: 4662803 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.2535. Min Act: -0.1700
Data Index: 8735948 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.2223. Min Act: -0.1700
Data Index: 3239344 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.2223. Min Act: -0.1700
Data Index: 1097183 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.2223. Min Act: -0.1700
Data Index: 5826287 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1910. Min Act: -0.1700
Data Index: 2664713 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1598. Min Act: -0.1700
Data Index: 8697830 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1910. Min Act: -0.1700
Data Index: 1780891 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1598. Min Act: -0.1700
Data Index: 2424535 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1285. Min Act: -0.1700
Data Index: 8624546 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1285. Min Act: -0.1700
Data Index: 8480721 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1598. Min Act: -0.1700
Data Index: 7125380 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1285. Min Act: -0.1700
Data Index: 3352349 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1285. Min Act: -0.1700
Data Index: 44068 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1285. Min Act: -0.1700
Data Index: 2494703 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.1285. Min Act: -0.1700
Data Index: 2113522 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.0973. Min Act: -0.1700
Data Index: 5904415 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4098. Min Range: -6.4098
Max Act: 6.0973. Min Act: -0.1700
Data Index: 525759 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19