Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3089. Min Range: -5.3089
Max Act: 5.3089. Min Act: -0.1700
Data Index: 5884694 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3089. Min Range: -5.3089
Max Act: 5.0277. Min Act: -0.1699
Data Index: 2183458 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.7777. Min Act: -0.1700
Data Index: 4901920 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.6839. Min Act: -0.1700
Data Index: 3888533 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.5902. Min Act: -0.1700
Data Index: 438263 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.5902. Min Act: -0.1700
Data Index: 8156639 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.5589. Min Act: -0.1700
Data Index: 7017315 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.5277. Min Act: -0.1700
Data Index: 5322306 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.5277. Min Act: -0.1700
Data Index: 6394823 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.4964. Min Act: -0.1700
Data Index: 4250248 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.5277. Min Act: -0.1700
Data Index: 4876875 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.4652. Min Act: -0.1700
Data Index: 6282558 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.4964. Min Act: -0.1700
Data Index: 2191765 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.4027. Min Act: -0.1700
Data Index: 5459837 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.4339. Min Act: -0.1700
Data Index: 3917994 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.3714. Min Act: -0.1700
Data Index: 1673698 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.4027. Min Act: -0.1700
Data Index: 6919166 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.3714. Min Act: -0.1700
Data Index: 8224430 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.4027. Min Act: -0.1700
Data Index: 4703556 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3089. Min Range: -5.3089
Max Act: 4.3089. Min Act: -0.1700
Data Index: 4735939 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19