Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.6936. Min Act: -0.1700
Data Index: 6328422 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.6623. Min Act: -0.1700
Data Index: 3840664 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.5998. Min Act: -0.1700
Data Index: 1980483 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.5998. Min Act: -0.1700
Data Index: 1509975 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.5686. Min Act: -0.1700
Data Index: 6717288 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.5373. Min Act: -0.1700
Data Index: 1627437 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.5061. Min Act: -0.1700
Data Index: 824065 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.5061. Min Act: -0.1700
Data Index: 7450866 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4748. Min Act: -0.1700
Data Index: 1944116 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4748. Min Act: -0.1700
Data Index: 6810434 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4123. Min Act: -0.1700
Data Index: 2673535 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4436. Min Act: -0.1700
Data Index: 8178703 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4436. Min Act: -0.1700
Data Index: 5047649 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4436. Min Act: -0.1700
Data Index: 7101533 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4123. Min Act: -0.1700
Data Index: 5746338 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4123. Min Act: -0.1700
Data Index: 6561967 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.4123. Min Act: -0.1700
Data Index: 8433229 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.3811. Min Act: -0.1700
Data Index: 5954004 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.3811. Min Act: -0.1700
Data Index: 1550320 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6936. Min Range: -5.6936
Max Act: 5.3811. Min Act: -0.1700
Data Index: 3359668 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19