Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.3514. Min Act: -0.1700
Data Index: 3933874 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.3201. Min Act: -0.1700
Data Index: 664362 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.2576. Min Act: -0.1700
Data Index: 910347 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.2264. Min Act: -0.1700
Data Index: 8156172 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1951. Min Act: -0.1700
Data Index: 5876586 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1639. Min Act: -0.1700
Data Index: 1914813 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1639. Min Act: -0.1700
Data Index: 2585004 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1951. Min Act: -0.1700
Data Index: 3620623 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1951. Min Act: -0.1700
Data Index: 6717191 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1639. Min Act: -0.1700
Data Index: 3946570 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1326. Min Act: -0.1700
Data Index: 6759960 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1326. Min Act: -0.1700
Data Index: 8473408 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1326. Min Act: -0.1700
Data Index: 6026899 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1326. Min Act: -0.1700
Data Index: 127418 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1014. Min Act: -0.1700
Data Index: 5070667 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.1014. Min Act: -0.1700
Data Index: 7032273 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.0701. Min Act: -0.1700
Data Index: 1248197 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.0389. Min Act: -0.1700
Data Index: 2015606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.0701. Min Act: -0.1700
Data Index: 4326231 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3514. Min Range: -4.3514
Max Act: 4.0389. Min Act: -0.1700
Data Index: 6871262 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19