Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2060 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.4780. Min Act: -0.1700
Data Index: 6495709 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.4467. Min Act: -0.1700
Data Index: 875115 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.3842. Min Act: -0.1700
Data Index: 3720814 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.3217. Min Act: -0.1700
Data Index: 3234106 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.3217. Min Act: -0.1700
Data Index: 7744156 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2280. Min Act: -0.1700
Data Index: 4900914 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2280. Min Act: -0.1700
Data Index: 970238 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2280. Min Act: -0.1700
Data Index: 1904877 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2280. Min Act: -0.1700
Data Index: 6618836 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1967. Min Act: -0.1700
Data Index: 6068905 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1967. Min Act: -0.1700
Data Index: 1812571 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1967. Min Act: -0.1700
Data Index: 6589988 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1967. Min Act: -0.1700
Data Index: 3006505 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1655. Min Act: -0.1700
Data Index: 7147398 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1342. Min Act: -0.1700
Data Index: 7257236 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1030. Min Act: -0.1700
Data Index: 1480483 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1030. Min Act: -0.1700
Data Index: 2137517 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1030. Min Act: -0.1700
Data Index: 3037084 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1030. Min Act: -0.1700
Data Index: 6102655 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1030. Min Act: -0.1700
Data Index: 672247 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19