Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1431 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.6567. Min Act: -0.1700
Data Index: 4262796 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.5942. Min Act: -0.1700
Data Index: 7302534 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.4692. Min Act: -0.1700
Data Index: 3337551 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.3442. Min Act: -0.1700
Data Index: 2410006 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.4067. Min Act: -0.1700
Data Index: 3289284 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.2817. Min Act: -0.1700
Data Index: 6409811 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.1567. Min Act: -0.1700
Data Index: 530169 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.1567. Min Act: -0.1700
Data Index: 1762029 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.1567. Min Act: -0.1700
Data Index: 664551 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.0942. Min Act: -0.1700
Data Index: 2677519 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.0942. Min Act: -0.1700
Data Index: 5129215 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.0317. Min Act: -0.1700
Data Index: 8810613 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.0317. Min Act: -0.1700
Data Index: 6247205 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.0004. Min Act: -0.1700
Data Index: 774695 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6567. Min Range: -8.6567
Max Act: 8.0004. Min Act: -0.1700
Data Index: 774692 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6567. Min Range: -8.6567
Max Act: 7.9692. Min Act: -0.1700
Data Index: 7604518 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6567. Min Range: -8.6567
Max Act: 7.9379. Min Act: -0.1700
Data Index: 790201 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6567. Min Range: -8.6567
Max Act: 7.9692. Min Act: -0.1700
Data Index: 8593405 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6567. Min Range: -8.6567
Max Act: 7.9379. Min Act: -0.1700
Data Index: 6172879 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6567. Min Range: -8.6567
Max Act: 7.9379. Min Act: -0.1700
Data Index: 4225331 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19