Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.6760. Min Act: -0.1700
Data Index: 4643847 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.3947. Min Act: -0.1700
Data Index: 5933411 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.3635. Min Act: -0.1700
Data Index: 7163174 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.3010. Min Act: -0.1700
Data Index: 1991212 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.3010. Min Act: -0.1700
Data Index: 168918 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.2697. Min Act: -0.1700
Data Index: 5760439 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.2385. Min Act: -0.1700
Data Index: 7825637 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.2385. Min Act: -0.1700
Data Index: 8383897 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.2072. Min Act: -0.1700
Data Index: 5294797 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.2072. Min Act: -0.1700
Data Index: 3232183 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.2072. Min Act: -0.1700
Data Index: 2451414 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1447. Min Act: -0.1700
Data Index: 8307352 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.1135. Min Act: -0.1700
Data Index: 3911609 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0822. Min Act: -0.1700
Data Index: 3851495 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0822. Min Act: -0.1700
Data Index: 5451051 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0822. Min Act: -0.1700
Data Index: 6135908 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0822. Min Act: -0.1700
Data Index: 5820057 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0822. Min Act: -0.1700
Data Index: 6222407 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0822. Min Act: -0.1700
Data Index: 4354192 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6760. Min Range: -6.6760
Max Act: 6.0510. Min Act: -0.1700
Data Index: 2734292 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19