Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1362. Min Range: -9.1362
Max Act: 9.1362. Min Act: -0.1700
Data Index: 3283078 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.7612. Min Act: -0.1700
Data Index: 5561371 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.6987. Min Act: -0.1700
Data Index: 5561373 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.6987. Min Act: -0.1700
Data Index: 3235270 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.6987. Min Act: -0.1700
Data Index: 5561372 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.6362. Min Act: -0.1700
Data Index: 3747300 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.5737. Min Act: -0.1700
Data Index: 4832134 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.4487. Min Act: -0.1700
Data Index: 6067321 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.4487. Min Act: -0.1700
Data Index: 3235272 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.3237. Min Act: -0.1700
Data Index: 3096892 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.3862. Min Act: -0.1700
Data Index: 8642771 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.3237. Min Act: -0.1700
Data Index: 3747297 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.3237. Min Act: -0.1700
Data Index: 1111932 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.3237. Min Act: -0.1700
Data Index: 4832118 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.2612. Min Act: -0.1700
Data Index: 3092581 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.2300. Min Act: -0.1700
Data Index: 63954 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.2612. Min Act: -0.1700
Data Index: 3096891 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.1987. Min Act: -0.1700
Data Index: 3092582 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.1987. Min Act: -0.1700
Data Index: 7220510 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1362. Min Range: -9.1362
Max Act: 8.2300. Min Act: -0.1700
Data Index: 8642770 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19