Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.1652. Min Act: -0.1700
Data Index: 6066053 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.1339. Min Act: -0.1700
Data Index: 8297027 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.0714. Min Act: -0.1700
Data Index: 1399990 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.0714. Min Act: -0.1700
Data Index: 2005753 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.0714. Min Act: -0.1700
Data Index: 6152814 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.0402. Min Act: -0.1700
Data Index: 7918790 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.0402. Min Act: -0.1700
Data Index: 7979943 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.0089. Min Act: -0.1700
Data Index: 6242763 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.0402. Min Act: -0.1700
Data Index: 3952735 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1652. Min Range: -6.1652
Max Act: 6.0089. Min Act: -0.1700
Data Index: 8612663 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.9777. Min Act: -0.1700
Data Index: 7363922 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.9464. Min Act: -0.1700
Data Index: 4902067 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.8839. Min Act: -0.1700
Data Index: 4230587 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.8527. Min Act: -0.1700
Data Index: 7340801 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.8527. Min Act: -0.1700
Data Index: 2704607 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.8214. Min Act: -0.1700
Data Index: 5480110 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.8214. Min Act: -0.1700
Data Index: 8121521 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.7902. Min Act: -0.1700
Data Index: 5488024 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.7589. Min Act: -0.1700
Data Index: 4433919 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1652. Min Range: -6.1652
Max Act: 5.7589. Min Act: -0.1700
Data Index: 3567055 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19