Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0719. Min Range: -5.0719
Max Act: 5.0719. Min Act: -0.1700
Data Index: 8467121 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0719. Min Range: -5.0719
Max Act: 5.0406. Min Act: -0.1700
Data Index: 4155162 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0719. Min Range: -5.0719
Max Act: 5.0094. Min Act: -0.1700
Data Index: 6146555 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.9781. Min Act: -0.1700
Data Index: 6544274 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.9781. Min Act: -0.1700
Data Index: 991693 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.9469. Min Act: -0.1700
Data Index: 6187477 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.9469. Min Act: -0.1700
Data Index: 5817482 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.9156. Min Act: -0.1700
Data Index: 7108289 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8844. Min Act: -0.1700
Data Index: 3568778 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8531. Min Act: -0.1700
Data Index: 3655585 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8531. Min Act: -0.1700
Data Index: 4039673 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8531. Min Act: -0.1700
Data Index: 253550 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8219. Min Act: -0.1700
Data Index: 6966278 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8219. Min Act: -0.1700
Data Index: 1618849 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8219. Min Act: -0.1700
Data Index: 4880883 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8219. Min Act: -0.1700
Data Index: 1770290 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8219. Min Act: -0.1700
Data Index: 1229910 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.7594. Min Act: -0.1700
Data Index: 5277199 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.8219. Min Act: -0.1700
Data Index: 5429653 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0719. Min Range: -5.0719
Max Act: 4.7906. Min Act: -0.1700
Data Index: 4514491 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19