Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2284 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4487. Min Range: -8.4487
Max Act: 8.4487. Min Act: -0.1700
Data Index: 2779422 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4487. Min Range: -8.4487
Max Act: 8.1362. Min Act: -0.1700
Data Index: 8105033 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4487. Min Range: -8.4487
Max Act: 8.1362. Min Act: -0.1700
Data Index: 995372 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4487. Min Range: -8.4487
Max Act: 8.0737. Min Act: -0.1700
Data Index: 3193285 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4487. Min Range: -8.4487
Max Act: 8.0737. Min Act: -0.1700
Data Index: 6437001 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4487. Min Range: -8.4487
Max Act: 8.0112. Min Act: -0.1700
Data Index: 6138301 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.9487. Min Act: -0.1700
Data Index: 7024487 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8862. Min Act: -0.1700
Data Index: 7340899 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8862. Min Act: -0.1700
Data Index: 2863757 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8237. Min Act: -0.1700
Data Index: 4339418 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8237. Min Act: -0.1700
Data Index: 936105 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8237. Min Act: -0.1700
Data Index: 3764727 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8237. Min Act: -0.1700
Data Index: 1286837 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8237. Min Act: -0.1700
Data Index: 8549341 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8237. Min Act: -0.1700
Data Index: 6195625 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8237. Min Act: -0.1700
Data Index: 1553048 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.8237. Min Act: -0.1700
Data Index: 4109091 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.7612. Min Act: -0.1700
Data Index: 9788 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.7612. Min Act: -0.1700
Data Index: 4792248 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4487. Min Range: -8.4487
Max Act: 7.7612. Min Act: -0.1700
Data Index: 7675733 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19