Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2258 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2941. Min Act: -0.1700
Data Index: 4134981 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 3361546 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 4280737 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 2470519 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 1438893 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 8354913 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2628. Min Act: -0.1700
Data Index: 4752905 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2316. Min Act: -0.1700
Data Index: 7557140 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.2003. Min Act: -0.1700
Data Index: 944766 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1691. Min Act: -0.1700
Data Index: 2014630 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1691. Min Act: -0.1700
Data Index: 7999193 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1691. Min Act: -0.1700
Data Index: 7807890 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1378. Min Act: -0.1700
Data Index: 2266442 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1691. Min Act: -0.1700
Data Index: 3212325 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1378. Min Act: -0.1700
Data Index: 8549438 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1378. Min Act: -0.1700
Data Index: 6172839 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1066. Min Act: -0.1700
Data Index: 5657534 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1066. Min Act: -0.1700
Data Index: 6084365 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.0753. Min Act: -0.1700
Data Index: 6119838 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2941. Min Range: -6.2941
Max Act: 6.1066. Min Act: -0.1700
Data Index: 4457880 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19