Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5850 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.9715. Min Act: -0.1700
Data Index: 2383798 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.9403. Min Act: -0.1700
Data Index: 4862891 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.8152. Min Act: -0.1700
Data Index: 5893696 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.7214. Min Act: -0.1700
Data Index: 3732066 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.7527. Min Act: -0.1700
Data Index: 6589804 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.6588. Min Act: -0.1700
Data Index: 5044123 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.6275. Min Act: -0.1700
Data Index: 110078 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5962. Min Act: -0.1700
Data Index: 2299016 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5962. Min Act: -0.1700
Data Index: 2169643 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5962. Min Act: -0.1700
Data Index: 4541192 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5649. Min Act: -0.1700
Data Index: 6312981 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5962. Min Act: -0.1700
Data Index: 3573424 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5962. Min Act: -0.1700
Data Index: 2465323 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5649. Min Act: -0.1700
Data Index: 470529 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5649. Min Act: -0.1700
Data Index: 1985077 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5336. Min Act: -0.1700
Data Index: 3691833 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5649. Min Act: -0.1700
Data Index: 7754821 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5649. Min Act: -0.1700
Data Index: 6247175 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5336. Min Act: -0.1700
Data Index: 3713833 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9715. Min Range: -3.9715
Max Act: 3.5023. Min Act: -0.1700
Data Index: 1360485 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19