Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 628 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0701. Min Range: -8.0701
Max Act: 8.0701. Min Act: -0.1700
Data Index: 7335173 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0701. Min Range: -8.0701
Max Act: 8.0076. Min Act: -0.1700
Data Index: 8739823 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.7576. Min Act: -0.1700
Data Index: 3953249 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.7264. Min Act: -0.1700
Data Index: 3761632 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.6326. Min Act: -0.1700
Data Index: 8762956 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.6014. Min Act: -0.1700
Data Index: 5675399 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.5701. Min Act: -0.1700
Data Index: 8434145 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.5076. Min Act: -0.1700
Data Index: 2691990 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.4764. Min Act: -0.1700
Data Index: 6402782 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.4764. Min Act: -0.1700
Data Index: 7349752 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.4451. Min Act: -0.1700
Data Index: 8049187 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.4139. Min Act: -0.1700
Data Index: 870293 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.4139. Min Act: -0.1700
Data Index: 4032711 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.3826. Min Act: -0.1700
Data Index: 2310224 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.3201. Min Act: -0.1700
Data Index: 4689871 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.3514. Min Act: -0.1700
Data Index: 195826 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.2889. Min Act: -0.1700
Data Index: 8505856 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.2576. Min Act: -0.1700
Data Index: 4560292 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.2576. Min Act: -0.1700
Data Index: 6945202 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0701. Min Range: -8.0701
Max Act: 7.2264. Min Act: -0.1700
Data Index: 880195 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19