Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0673. Min Range: -5.0673
Max Act: 5.0673. Min Act: -0.1700
Data Index: 5371543 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0673. Min Range: -5.0673
Max Act: 5.0048. Min Act: -0.1700
Data Index: 1859777 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.9423. Min Act: -0.1700
Data Index: 4678857 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.8798. Min Act: -0.1700
Data Index: 6558290 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.8798. Min Act: -0.1700
Data Index: 1057649 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.8485. Min Act: -0.1700
Data Index: 3476058 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7860. Min Act: -0.1700
Data Index: 6167203 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7860. Min Act: -0.1700
Data Index: 8822254 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7860. Min Act: -0.1700
Data Index: 7657295 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7860. Min Act: -0.1700
Data Index: 2862496 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7860. Min Act: -0.1700
Data Index: 2675546 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7548. Min Act: -0.1700
Data Index: 4678867 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7548. Min Act: -0.1700
Data Index: 898052 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7548. Min Act: -0.1700
Data Index: 308534 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7548. Min Act: -0.1700
Data Index: 5937932 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7548. Min Act: -0.1700
Data Index: 7401745 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7235. Min Act: -0.1700
Data Index: 4375413 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7235. Min Act: -0.1700
Data Index: 2034498 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7235. Min Act: -0.1700
Data Index: 1610322 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0673. Min Range: -5.0673
Max Act: 4.7235. Min Act: -0.1700
Data Index: 5669774 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19