Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.6668. Min Act: -0.1700
Data Index: 6915280 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.6355. Min Act: -0.1700
Data Index: 891864 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.4793. Min Act: -0.1700
Data Index: 1048855 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.4793. Min Act: -0.1700
Data Index: 1399134 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.4480. Min Act: -0.1700
Data Index: 3041816 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.3543. Min Act: -0.1700
Data Index: 1644726 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.3855. Min Act: -0.1700
Data Index: 44242 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.3543. Min Act: -0.1700
Data Index: 2729294 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.3543. Min Act: -0.1700
Data Index: 2130942 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.3230. Min Act: -0.1700
Data Index: 2560273 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.3230. Min Act: -0.1700
Data Index: 457395 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2918. Min Act: -0.1700
Data Index: 1476789 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2918. Min Act: -0.1700
Data Index: 4305217 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2918. Min Act: -0.1700
Data Index: 8059726 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2918. Min Act: -0.1700
Data Index: 4134506 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2918. Min Act: -0.1700
Data Index: 2892687 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2918. Min Act: -0.1700
Data Index: 7825488 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2918. Min Act: -0.1700
Data Index: 2853934 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2918. Min Act: -0.1700
Data Index: 6086995 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6668. Min Range: -6.6668
Max Act: 6.2605. Min Act: -0.1700
Data Index: 7532484 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19