Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2171 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.8766. Min Act: -0.1700
Data Index: 3699156 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.8453. Min Act: -0.1700
Data Index: 5468493 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.8453. Min Act: -0.1700
Data Index: 7463840 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.7828. Min Act: -0.1700
Data Index: 6967313 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.7828. Min Act: -0.1700
Data Index: 6265336 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.7828. Min Act: -0.1700
Data Index: 8541766 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.8141. Min Act: -0.1700
Data Index: 1286094 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.7516. Min Act: -0.1700
Data Index: 4785230 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.7516. Min Act: -0.1700
Data Index: 3135594 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.7203. Min Act: -0.1700
Data Index: 7339357 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.7203. Min Act: -0.1700
Data Index: 3760446 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6578. Min Act: -0.1700
Data Index: 5792553 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6891. Min Act: -0.1700
Data Index: 8461754 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6891. Min Act: -0.1700
Data Index: 4901813 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6578. Min Act: -0.1700
Data Index: 7286210 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6578. Min Act: -0.1700
Data Index: 5533574 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6891. Min Act: -0.1700
Data Index: 8121173 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6891. Min Act: -0.1700
Data Index: 6737291 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6266. Min Act: -0.1700
Data Index: 6115097 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8766. Min Range: -6.8766
Max Act: 6.6266. Min Act: -0.1700
Data Index: 2750485 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19