Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.7664. Min Act: -0.1700
Data Index: 5960311 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.5164. Min Act: -0.1700
Data Index: 2681510 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.2664. Min Act: -0.1700
Data Index: 1645575 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.2664. Min Act: -0.1700
Data Index: 3791480 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.2352. Min Act: -0.1700
Data Index: 3235652 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.2352. Min Act: -0.1700
Data Index: 2688631 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.2039. Min Act: -0.1700
Data Index: 2314315 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.2039. Min Act: -0.1700
Data Index: 3124797 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.1102. Min Act: -0.1700
Data Index: 6847141 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.1102. Min Act: -0.1700
Data Index: 2568842 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0789. Min Act: -0.1700
Data Index: 3371809 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0789. Min Act: -0.1700
Data Index: 183803 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0477. Min Act: -0.1700
Data Index: 7231099 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0477. Min Act: -0.1700
Data Index: 8140084 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0477. Min Act: -0.1700
Data Index: 486276 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0789. Min Act: -0.1700
Data Index: 3979820 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0164. Min Act: -0.1700
Data Index: 1844969 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0164. Min Act: -0.1700
Data Index: 2488071 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0477. Min Act: -0.1700
Data Index: 4844617 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7664. Min Range: -5.7664
Max Act: 5.0164. Min Act: -0.1700
Data Index: 788479 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19