Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.8160. Min Act: -0.1700
Data Index: 3703768 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.6285. Min Act: -0.1700
Data Index: 813754 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.4410. Min Act: -0.1700
Data Index: 1001054 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.4410. Min Act: -0.1700
Data Index: 8484489 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.4098. Min Act: -0.1700
Data Index: 880550 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.3785. Min Act: -0.1700
Data Index: 1281004 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.3785. Min Act: -0.1700
Data Index: 3658299 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.3473. Min Act: -0.1700
Data Index: 4463815 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2848. Min Act: -0.1700
Data Index: 1480 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2848. Min Act: -0.1700
Data Index: 3152933 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2848. Min Act: -0.1700
Data Index: 3492621 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2848. Min Act: -0.1700
Data Index: 5684711 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2535. Min Act: -0.1700
Data Index: 1611666 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2535. Min Act: -0.1700
Data Index: 1375413 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2222. Min Act: -0.1700
Data Index: 5684710 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2222. Min Act: -0.1700
Data Index: 4354689 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2535. Min Act: -0.1700
Data Index: 2789093 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.2222. Min Act: -0.1700
Data Index: 2560168 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.1910. Min Act: -0.1700
Data Index: 926642 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8160. Min Range: -4.8160
Max Act: 4.1910. Min Act: -0.1700
Data Index: 3014097 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19