Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1765 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.7386. Min Act: -0.1700
Data Index: 8334026 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.7073. Min Act: -0.1700
Data Index: 2744922 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.6761. Min Act: -0.1700
Data Index: 3068026 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.4886. Min Act: -0.1700
Data Index: 2845728 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.4573. Min Act: -0.1700
Data Index: 4083064 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.4261. Min Act: -0.1700
Data Index: 1120046 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.3323. Min Act: -0.1700
Data Index: 6745061 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.3323. Min Act: -0.1700
Data Index: 8174013 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.3323. Min Act: -0.1700
Data Index: 5800088 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.3323. Min Act: -0.1700
Data Index: 1511514 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.3323. Min Act: -0.1700
Data Index: 2123160 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.3323. Min Act: -0.1700
Data Index: 8566737 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.3323. Min Act: -0.1700
Data Index: 3468304 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.2698. Min Act: -0.1700
Data Index: 7498466 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.2698. Min Act: -0.1700
Data Index: 1216502 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.2698. Min Act: -0.1700
Data Index: 5052172 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.2698. Min Act: -0.1700
Data Index: 5573980 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.2698. Min Act: -0.1700
Data Index: 6519889 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.2386. Min Act: -0.1700
Data Index: 7399711 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7386. Min Range: -6.7386
Max Act: 6.2073. Min Act: -0.1700
Data Index: 3487279 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19