Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.5753. Min Act: -0.1700
Data Index: 1993055 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.5753. Min Act: -0.1700
Data Index: 8532838 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.5128. Min Act: -0.1700
Data Index: 286139 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.5128. Min Act: -0.1700
Data Index: 7391403 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.5128. Min Act: -0.1700
Data Index: 5634381 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.4816. Min Act: -0.1700
Data Index: 7752930 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.4503. Min Act: -0.1700
Data Index: 7502320 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.3566. Min Act: -0.1700
Data Index: 6839211 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.3566. Min Act: -0.1700
Data Index: 4892937 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.3566. Min Act: -0.1700
Data Index: 3292942 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.3566. Min Act: -0.1700
Data Index: 8577298 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.3253. Min Act: -0.1700
Data Index: 3527927 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.2941. Min Act: -0.1700
Data Index: 2436219 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.2941. Min Act: -0.1700
Data Index: 2910239 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.2628. Min Act: -0.1700
Data Index: 3923648 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.2003. Min Act: -0.1700
Data Index: 665862 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.2003. Min Act: -0.1700
Data Index: 4757310 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.2003. Min Act: -0.1700
Data Index: 2161836 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.2003. Min Act: -0.1700
Data Index: 2086031 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5753. Min Range: -7.5753
Max Act: 7.2003. Min Act: -0.1700
Data Index: 6007220 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19