Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4683 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0399. Min Range: -7.0399
Max Act: 7.0399. Min Act: -0.1700
Data Index: 4839576 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.7274. Min Act: -0.1700
Data Index: 5697152 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6649. Min Act: -0.1700
Data Index: 6862874 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6336. Min Act: -0.1700
Data Index: 471291 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.6024. Min Act: -0.1700
Data Index: 4612137 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5711. Min Act: -0.1700
Data Index: 8249840 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 2390957 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5399. Min Act: -0.1700
Data Index: 6099575 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5086. Min Act: -0.1700
Data Index: 3238953 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5086. Min Act: -0.1700
Data Index: 8111813 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.5086. Min Act: -0.1700
Data Index: 1982035 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4461. Min Act: -0.1700
Data Index: 1722838 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4774. Min Act: -0.1700
Data Index: 2338063 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4461. Min Act: -0.1700
Data Index: 4507432 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4149. Min Act: -0.1700
Data Index: 1619846 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.3836. Min Act: -0.1700
Data Index: 2311572 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.4149. Min Act: -0.1700
Data Index: 6521088 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.3836. Min Act: -0.1700
Data Index: 1999535 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.3524. Min Act: -0.1700
Data Index: 3225017 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0399. Min Range: -7.0399
Max Act: 6.3524. Min Act: -0.1700
Data Index: 7504193 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19