Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4866 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.5066. Min Act: -0.1700
Data Index: 8758890 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.4753. Min Act: -0.1700
Data Index: 5950372 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.3191. Min Act: -0.1700
Data Index: 2711259 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.2566. Min Act: -0.1700
Data Index: 1939230 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.2253. Min Act: -0.1700
Data Index: 5001220 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.1941. Min Act: -0.1700
Data Index: 3851873 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.1941. Min Act: -0.1700
Data Index: 55310 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.1628. Min Act: -0.1700
Data Index: 7959100 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.1316. Min Act: -0.1700
Data Index: 2775271 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.1316. Min Act: -0.1700
Data Index: 40408 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0691. Min Act: -0.1700
Data Index: 6475973 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0378. Min Act: -0.1700
Data Index: 6548502 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0691. Min Act: -0.1700
Data Index: 6943019 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0378. Min Act: -0.1700
Data Index: 156981 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0691. Min Act: -0.1700
Data Index: 2480974 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0691. Min Act: -0.1700
Data Index: 6424223 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0378. Min Act: -0.1700
Data Index: 4546850 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0378. Min Act: -0.1700
Data Index: 2822213 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0378. Min Act: -0.1700
Data Index: 8442670 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5066. Min Range: -5.5066
Max Act: 5.0378. Min Act: -0.1700
Data Index: 37304 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19