Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3136. Min Range: -4.3136
Max Act: 4.3136. Min Act: -0.1700
Data Index: 2309274 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3136. Min Range: -4.3136
Max Act: 4.3136. Min Act: -0.1700
Data Index: 2264343 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3136. Min Range: -4.3136
Max Act: 4.1260. Min Act: -0.1700
Data Index: 5683316 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3136. Min Range: -4.3136
Max Act: 4.1573. Min Act: -0.1700
Data Index: 1568355 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3136. Min Range: -4.3136
Max Act: 4.0323. Min Act: -0.1700
Data Index: 799059 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3136. Min Range: -4.3136
Max Act: 4.0323. Min Act: -0.1700
Data Index: 5084944 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3136. Min Range: -4.3136
Max Act: 4.0323. Min Act: -0.1700
Data Index: 99866 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.9697. Min Act: -0.1700
Data Index: 827487 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.9385. Min Act: -0.1700
Data Index: 2586002 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.9385. Min Act: -0.1700
Data Index: 5497689 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.9072. Min Act: -0.1700
Data Index: 5555835 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.9697. Min Act: -0.1700
Data Index: 5646601 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.9072. Min Act: -0.1700
Data Index: 4008677 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.9072. Min Act: -0.1700
Data Index: 4818301 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.8447. Min Act: -0.1700
Data Index: 2219141 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.9385. Min Act: -0.1700
Data Index: 1416484 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.8759. Min Act: -0.1700
Data Index: 1871428 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.8447. Min Act: -0.1700
Data Index: 488669 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.8759. Min Act: -0.1700
Data Index: 22790 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3136. Min Range: -4.3136
Max Act: 3.8759. Min Act: -0.1700
Data Index: 69587 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19