Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6822. Min Range: -7.6822
Max Act: 7.6822. Min Act: -0.1700
Data Index: 3028757 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6822. Min Range: -7.6822
Max Act: 7.4322. Min Act: -0.1700
Data Index: 3248648 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6822. Min Range: -7.6822
Max Act: 7.3072. Min Act: -0.1700
Data Index: 7263660 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6822. Min Range: -7.6822
Max Act: 7.3072. Min Act: -0.1700
Data Index: 7263662 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6822. Min Range: -7.6822
Max Act: 7.0885. Min Act: -0.1700
Data Index: 6194245 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.9947. Min Act: -0.1700
Data Index: 3290691 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.9010. Min Act: -0.1700
Data Index: 7282822 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.8697. Min Act: -0.1700
Data Index: 375572 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.8697. Min Act: -0.1700
Data Index: 1976741 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.8072. Min Act: -0.1700
Data Index: 7818216 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.9010. Min Act: -0.1700
Data Index: 7332229 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.7760. Min Act: -0.1700
Data Index: 3821345 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.8072. Min Act: -0.1700
Data Index: 1952368 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.8072. Min Act: -0.1700
Data Index: 4659823 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.7447. Min Act: -0.1700
Data Index: 496861 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.6510. Min Act: -0.1700
Data Index: 4032635 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.6510. Min Act: -0.1700
Data Index: 7818232 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.6197. Min Act: -0.1700
Data Index: 6412622 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.6197. Min Act: -0.1700
Data Index: 123040 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6822. Min Range: -7.6822
Max Act: 6.5885. Min Act: -0.1700
Data Index: 4745070 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19