Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2516 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1572. Min Range: -8.1572
Max Act: 8.1572. Min Act: -0.1700
Data Index: 3503425 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1572. Min Range: -8.1572
Max Act: 8.0322. Min Act: -0.1700
Data Index: 4823160 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9697. Min Act: -0.1700
Data Index: 6142519 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9697. Min Act: -0.1700
Data Index: 7930237 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9697. Min Act: -0.1700
Data Index: 4949467 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9697. Min Act: -0.1700
Data Index: 526492 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9697. Min Act: -0.1700
Data Index: 4072636 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9072. Min Act: -0.1700
Data Index: 3294001 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9072. Min Act: -0.1700
Data Index: 4992287 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9072. Min Act: -0.1700
Data Index: 4013839 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9072. Min Act: -0.1700
Data Index: 4588570 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9072. Min Act: -0.1700
Data Index: 8509856 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.9072. Min Act: -0.1700
Data Index: 4300170 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.8447. Min Act: -0.1700
Data Index: 2984397 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.8447. Min Act: -0.1700
Data Index: 601224 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.8447. Min Act: -0.1700
Data Index: 2398671 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.7822. Min Act: -0.1700
Data Index: 1347541 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.7197. Min Act: -0.1700
Data Index: 4937874 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.7822. Min Act: -0.1700
Data Index: 1855204 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1572. Min Range: -8.1572
Max Act: 7.7822. Min Act: -0.1700
Data Index: 133838 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19