Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.3566. Min Act: -0.1700
Data Index: 2912577 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.3238. Min Act: -0.1700
Data Index: 6747276 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.3074. Min Act: -0.1700
Data Index: 4786039 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2909. Min Act: -0.1700
Data Index: 4557221 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2580. Min Act: -0.1700
Data Index: 5218595 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2580. Min Act: -0.1700
Data Index: 4933943 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2580. Min Act: -0.1700
Data Index: 8087147 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2745. Min Act: -0.1700
Data Index: 5539606 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2414. Min Act: -0.1700
Data Index: 4221179 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2414. Min Act: -0.1700
Data Index: 7773000 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2414. Min Act: -0.1700
Data Index: 5928971 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2249. Min Act: -0.1700
Data Index: 911640 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2249. Min Act: -0.1700
Data Index: 8806154 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2414. Min Act: -0.1700
Data Index: 2574592 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2249. Min Act: -0.1700
Data Index: 2006059 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2249. Min Act: -0.1698
Data Index: 2302462 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2249. Min Act: -0.1700
Data Index: 4503236 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.1917. Min Act: -0.1700
Data Index: 339189 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.1917. Min Act: -0.1700
Data Index: 7686290 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3566. Min Range: -2.3566
Max Act: 2.2083. Min Act: -0.1700
Data Index: 5437836 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19