Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3176 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.3947. Min Act: -0.1700
Data Index: 6977705 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.3322. Min Act: -0.1700
Data Index: 4830583 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.3009. Min Act: -0.1700
Data Index: 1635109 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.3009. Min Act: -0.1700
Data Index: 2225227 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.3009. Min Act: -0.1700
Data Index: 2987084 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2697. Min Act: -0.1700
Data Index: 734557 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2697. Min Act: -0.1700
Data Index: 2539602 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.3009. Min Act: -0.1700
Data Index: 7738872 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2697. Min Act: -0.1700
Data Index: 7458314 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2697. Min Act: -0.1700
Data Index: 2252049 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2697. Min Act: -0.1700
Data Index: 3438660 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2697. Min Act: -0.1700
Data Index: 1767608 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2072. Min Act: -0.1700
Data Index: 3041227 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2072. Min Act: -0.1700
Data Index: 3153167 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2072. Min Act: -0.1700
Data Index: 5140320 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.2072. Min Act: -0.1700
Data Index: 1608781 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.1759. Min Act: -0.1700
Data Index: 1969787 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.1759. Min Act: -0.1700
Data Index: 4655709 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.1447. Min Act: -0.1700
Data Index: 5288144 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3947. Min Range: -5.3947
Max Act: 5.1447. Min Act: -0.1700
Data Index: 5279202 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19