Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0153. Min Range: -7.0153
Max Act: 7.0153. Min Act: -0.1700
Data Index: 3034243 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.9841. Min Act: -0.1700
Data Index: 3347179 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.9841. Min Act: -0.1700
Data Index: 1987852 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.9528. Min Act: -0.1700
Data Index: 6223848 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.9528. Min Act: -0.1700
Data Index: 2424591 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.9216. Min Act: -0.1700
Data Index: 4938833 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.9216. Min Act: -0.1700
Data Index: 3246730 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.8903. Min Act: -0.1700
Data Index: 2138337 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.8903. Min Act: -0.1700
Data Index: 4561873 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.9216. Min Act: -0.1700
Data Index: 1373360 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.8591. Min Act: -0.1700
Data Index: 2419293 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.8278. Min Act: -0.1700
Data Index: 5936509 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.7653. Min Act: -0.1700
Data Index: 4715666 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.7966. Min Act: -0.1700
Data Index: 6444856 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.7966. Min Act: -0.1700
Data Index: 2493869 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.7341. Min Act: -0.1700
Data Index: 3547146 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.7028. Min Act: -0.1700
Data Index: 1867720 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.6716. Min Act: -0.1700
Data Index: 2007694 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.7341. Min Act: -0.1700
Data Index: 464613 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0153. Min Range: -7.0153
Max Act: 6.6716. Min Act: -0.1700
Data Index: 8463720 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19