Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4220 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.5597. Min Act: -0.1700
Data Index: 8485420 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.5597. Min Act: -0.1700
Data Index: 2601317 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.4347. Min Act: -0.1700
Data Index: 8524760 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.3409. Min Act: -0.1700
Data Index: 4542293 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.2784. Min Act: -0.1700
Data Index: 2113470 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.2784. Min Act: -0.1700
Data Index: 6031403 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.1534. Min Act: -0.1700
Data Index: 2937328 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.1534. Min Act: -0.1700
Data Index: 4018329 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.1534. Min Act: -0.1700
Data Index: 2937722 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.0909. Min Act: -0.1700
Data Index: 2195558 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.0597. Min Act: -0.1700
Data Index: 1925300 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5597. Min Range: -7.5597
Max Act: 7.0284. Min Act: -0.1700
Data Index: 5848494 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9972. Min Act: -0.1700
Data Index: 5298213 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9659. Min Act: -0.1700
Data Index: 949578 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9659. Min Act: -0.1700
Data Index: 4248161 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9659. Min Act: -0.1700
Data Index: 4015289 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9347. Min Act: -0.1700
Data Index: 2975252 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9034. Min Act: -0.1700
Data Index: 314642 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9347. Min Act: -0.1700
Data Index: 75387 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5597. Min Range: -7.5597
Max Act: 6.9034. Min Act: -0.1700
Data Index: 1540122 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19