Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5667 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1994. Min Range: -7.1994
Max Act: 7.1994. Min Act: -0.1700
Data Index: 138929 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1994. Min Range: -7.1994
Max Act: 7.0119. Min Act: -0.1700
Data Index: 6528580 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1994. Min Range: -7.1994
Max Act: 7.0119. Min Act: -0.1700
Data Index: 8637018 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.9807. Min Act: -0.1700
Data Index: 663682 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.9807. Min Act: -0.1700
Data Index: 321788 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.9494. Min Act: -0.1700
Data Index: 124423 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.9182. Min Act: -0.1700
Data Index: 1636315 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.9182. Min Act: -0.1700
Data Index: 5634489 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.8869. Min Act: -0.1700
Data Index: 7843782 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.8557. Min Act: -0.1700
Data Index: 1928075 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.8869. Min Act: -0.1700
Data Index: 5439970 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.8557. Min Act: -0.1700
Data Index: 7634037 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.8244. Min Act: -0.1700
Data Index: 3469462 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.8244. Min Act: -0.1700
Data Index: 1924568 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.7932. Min Act: -0.1700
Data Index: 6082141 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.8557. Min Act: -0.1700
Data Index: 7890393 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.8244. Min Act: -0.1700
Data Index: 661494 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.7932. Min Act: -0.1700
Data Index: 5612123 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.7307. Min Act: -0.1700
Data Index: 7896600 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1994. Min Range: -7.1994
Max Act: 6.7619. Min Act: -0.1700
Data Index: 5020932 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19