Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2102 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0906. Min Range: -8.0906
Max Act: 8.0906. Min Act: -0.1700
Data Index: 3739162 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.8406. Min Act: -0.1700
Data Index: 7807128 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.7781. Min Act: -0.1700
Data Index: 3853375 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.7156. Min Act: -0.1700
Data Index: 6620958 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.7156. Min Act: -0.1700
Data Index: 7719459 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.7156. Min Act: -0.1700
Data Index: 2352170 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.7156. Min Act: -0.1700
Data Index: 5535533 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.6531. Min Act: -0.1700
Data Index: 2468000 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.6531. Min Act: -0.1700
Data Index: 7852646 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.6218. Min Act: -0.1700
Data Index: 8155795 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.6218. Min Act: -0.1700
Data Index: 7739194 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.5906. Min Act: -0.1700
Data Index: 268570 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.5593. Min Act: -0.1700
Data Index: 1897068 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.5593. Min Act: -0.1700
Data Index: 7136868 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.5593. Min Act: -0.1700
Data Index: 4004550 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.5593. Min Act: -0.1700
Data Index: 8212118 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.5281. Min Act: -0.1700
Data Index: 6113046 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.4656. Min Act: -0.1700
Data Index: 5597009 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.4968. Min Act: -0.1700
Data Index: 8382199 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0906. Min Range: -8.0906
Max Act: 7.4968. Min Act: -0.1700
Data Index: 2747005 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19