Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4189. Min Range: -6.4189
Max Act: 6.4189. Min Act: -0.1700
Data Index: 1992725 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4189. Min Range: -6.4189
Max Act: 6.2002. Min Act: -0.1700
Data Index: 6392901 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4189. Min Range: -6.4189
Max Act: 6.1689. Min Act: -0.1700
Data Index: 4255327 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4189. Min Range: -6.4189
Max Act: 6.1689. Min Act: -0.1700
Data Index: 940520 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4189. Min Range: -6.4189
Max Act: 6.0752. Min Act: -0.1700
Data Index: 646240 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.9814. Min Act: -0.1700
Data Index: 157540 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.9814. Min Act: -0.1700
Data Index: 5969319 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.9189. Min Act: -0.1700
Data Index: 913738 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.9189. Min Act: -0.1700
Data Index: 5484278 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.8877. Min Act: -0.1700
Data Index: 7830853 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.8877. Min Act: -0.1700
Data Index: 7195315 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.8564. Min Act: -0.1700
Data Index: 3513203 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.8564. Min Act: -0.1700
Data Index: 615722 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.8252. Min Act: -0.1700
Data Index: 1092262 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.8252. Min Act: -0.1700
Data Index: 6194742 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.8252. Min Act: -0.1700
Data Index: 2520948 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.7939. Min Act: -0.1700
Data Index: 2861244 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.7939. Min Act: -0.1700
Data Index: 6319553 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.7939. Min Act: -0.1700
Data Index: 3680284 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4189. Min Range: -6.4189
Max Act: 5.7939. Min Act: -0.1700
Data Index: 1303980 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19