Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1865 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.8704. Min Act: -0.1700
Data Index: 2398320 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.7767. Min Act: -0.1700
Data Index: 5313202 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.7454. Min Act: -0.1700
Data Index: 4474949 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.7454. Min Act: -0.1700
Data Index: 162147 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.6829. Min Act: -0.1700
Data Index: 6195241 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.7142. Min Act: -0.1700
Data Index: 30657 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.7142. Min Act: -0.1700
Data Index: 385329 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.6829. Min Act: -0.1700
Data Index: 4454331 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.6517. Min Act: -0.1700
Data Index: 6762026 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.6517. Min Act: -0.1700
Data Index: 6908836 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.6517. Min Act: -0.1700
Data Index: 3372456 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.6517. Min Act: -0.1700
Data Index: 4054154 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.5892. Min Act: -0.1700
Data Index: 944913 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.5892. Min Act: -0.1700
Data Index: 3676831 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.5892. Min Act: -0.1700
Data Index: 5502495 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.5892. Min Act: -0.1700
Data Index: 3424677 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.5892. Min Act: -0.1700
Data Index: 3927520 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.5579. Min Act: -0.1700
Data Index: 2244482 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.5579. Min Act: -0.1700
Data Index: 2003115 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8704. Min Range: -6.8704
Max Act: 6.5579. Min Act: -0.1700
Data Index: 361084 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19