Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.9921. Min Act: -0.1700
Data Index: 6256763 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.7733. Min Act: -0.1700
Data Index: 5724018 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.7421. Min Act: -0.1700
Data Index: 7730291 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.7421. Min Act: -0.1700
Data Index: 2892 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.6483. Min Act: -0.1700
Data Index: 5715720 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.6796. Min Act: -0.1700
Data Index: 3056343 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.6796. Min Act: -0.1700
Data Index: 2451239 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.6483. Min Act: -0.1700
Data Index: 2427973 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.6171. Min Act: -0.1700
Data Index: 1848139 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.6171. Min Act: -0.1700
Data Index: 5812686 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.5858. Min Act: -0.1700
Data Index: 7882856 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.5858. Min Act: -0.1700
Data Index: 4246946 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.5233. Min Act: -0.1700
Data Index: 478218 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.5233. Min Act: -0.1700
Data Index: 4401811 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.4921. Min Act: -0.1700
Data Index: 4506726 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.4921. Min Act: -0.1700
Data Index: 2546630 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.4921. Min Act: -0.1700
Data Index: 3949795 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.5233. Min Act: -0.1700
Data Index: 6400307 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.4608. Min Act: -0.1700
Data Index: 6966879 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9921. Min Range: -4.9921
Max Act: 4.4921. Min Act: -0.1700
Data Index: 5082872 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19