Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.7479. Min Act: -0.1700
Data Index: 8127131 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.6540. Min Act: -0.1700
Data Index: 1333434 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5915. Min Act: -0.1700
Data Index: 4909509 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.5445. Min Act: -0.1700
Data Index: 2411031 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.4192. Min Act: -0.1700
Data Index: 5864742 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.4192. Min Act: -0.1700
Data Index: 6954536 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.4035. Min Act: -0.1700
Data Index: 6342024 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.4035. Min Act: -0.1700
Data Index: 1821088 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3564. Min Act: -0.1700
Data Index: 341606 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3721. Min Act: -0.1700
Data Index: 6269545 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3878. Min Act: -0.1700
Data Index: 8110437 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3721. Min Act: -0.1700
Data Index: 366869 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3564. Min Act: -0.1700
Data Index: 4208689 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3564. Min Act: -0.1700
Data Index: 3664257 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3564. Min Act: -0.1700
Data Index: 4320011 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3564. Min Act: -0.1700
Data Index: 1885263 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3408. Min Act: -0.1700
Data Index: 3405911 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3564. Min Act: -0.1700
Data Index: 4317411 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3251. Min Act: -0.1700
Data Index: 6813107 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7479. Min Range: -3.7479
Max Act: 3.3408. Min Act: -0.1700
Data Index: 6014355 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19