Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0055. Min Range: -5.0055
Max Act: 5.0055. Min Act: -0.1700
Data Index: 4589781 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9430. Min Act: -0.1700
Data Index: 6433242 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.9117. Min Act: -0.1700
Data Index: 7087832 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7867. Min Act: -0.1700
Data Index: 6773548 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7555. Min Act: -0.1700
Data Index: 53951 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7555. Min Act: -0.1700
Data Index: 1259992 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7555. Min Act: -0.1700
Data Index: 2365503 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7867. Min Act: -0.1700
Data Index: 2615768 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7242. Min Act: -0.1700
Data Index: 8684140 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7242. Min Act: -0.1700
Data Index: 4211979 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7242. Min Act: -0.1700
Data Index: 7981839 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.7242. Min Act: -0.1700
Data Index: 2496475 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.6930. Min Act: -0.1700
Data Index: 4584186 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.6930. Min Act: -0.1700
Data Index: 5322049 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.6930. Min Act: -0.1700
Data Index: 6355445 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.6930. Min Act: -0.1700
Data Index: 4912285 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.6930. Min Act: -0.1700
Data Index: 3767073 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.6930. Min Act: -0.1700
Data Index: 3959324 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.6930. Min Act: -0.1700
Data Index: 4012085 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0055. Min Range: -5.0055
Max Act: 4.6617. Min Act: -0.1700
Data Index: 7654018 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19