Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4420 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.4988. Min Act: -0.1700
Data Index: 3526564 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.3738. Min Act: -0.1700
Data Index: 6098798 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.3738. Min Act: -0.1700
Data Index: 2807664 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.2488. Min Act: -0.1700
Data Index: 1772982 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.2488. Min Act: -0.1700
Data Index: 8252953 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.1863. Min Act: -0.1700
Data Index: 1491018 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.1863. Min Act: -0.1700
Data Index: 7387567 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.1863. Min Act: -0.1700
Data Index: 6289260 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.1863. Min Act: -0.1700
Data Index: 6052423 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.1238. Min Act: -0.1700
Data Index: 6107123 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4988. Min Range: -9.4988
Max Act: 9.0613. Min Act: -0.1700
Data Index: 7051695 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9363. Min Act: -0.1700
Data Index: 6547761 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9988. Min Act: -0.1700
Data Index: 907289 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9363. Min Act: -0.1700
Data Index: 7343797 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9988. Min Act: -0.1700
Data Index: 3013679 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9988. Min Act: -0.1700
Data Index: 8337436 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9988. Min Act: -0.1700
Data Index: 5987597 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9988. Min Act: -0.1700
Data Index: 380035 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9988. Min Act: -0.1700
Data Index: 1691903 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4988. Min Range: -9.4988
Max Act: 8.9363. Min Act: -0.1700
Data Index: 2562199 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19