Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.9809. Min Act: -0.1700
Data Index: 7684453 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.8872. Min Act: -0.1700
Data Index: 7072198 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.6997. Min Act: -0.1700
Data Index: 6446764 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.4809. Min Act: -0.1700
Data Index: 3961149 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.3872. Min Act: -0.1700
Data Index: 7934930 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.4184. Min Act: -0.1700
Data Index: 2329416 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.3559. Min Act: -0.1700
Data Index: 8550003 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.3559. Min Act: -0.1700
Data Index: 3687065 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.3559. Min Act: -0.1700
Data Index: 6572442 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.3559. Min Act: -0.1700
Data Index: 677523 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.3559. Min Act: -0.1700
Data Index: 7315225 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.3247. Min Act: -0.1700
Data Index: 3879254 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.3247. Min Act: -0.1700
Data Index: 6503055 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.2934. Min Act: -0.1700
Data Index: 8187988 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.2622. Min Act: -0.1700
Data Index: 5501490 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.2309. Min Act: -0.1700
Data Index: 4235944 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.1684. Min Act: -0.1700
Data Index: 8745645 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.1997. Min Act: -0.1700
Data Index: 5141871 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.1372. Min Act: -0.1700
Data Index: 786539 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9809. Min Range: -6.9809
Max Act: 6.1372. Min Act: -0.1700
Data Index: 3036964 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19