Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 305 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.4572. Min Act: -0.1700
Data Index: 3583183 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.2697. Min Act: -0.1700
Data Index: 6064731 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.3010. Min Act: -0.1700
Data Index: 731436 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.2072. Min Act: -0.1700
Data Index: 2459031 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.2697. Min Act: -0.1700
Data Index: 6388755 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.1760. Min Act: -0.1700
Data Index: 2159013 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.1760. Min Act: -0.1700
Data Index: 8647795 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.2072. Min Act: -0.1700
Data Index: 7412657 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.1760. Min Act: -0.1700
Data Index: 744120 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.2072. Min Act: -0.1700
Data Index: 8730594 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.1135. Min Act: -0.1700
Data Index: 3570207 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.0510. Min Act: -0.1700
Data Index: 5284883 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.1135. Min Act: -0.1700
Data Index: 2160535 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.0822. Min Act: -0.1700
Data Index: 329724 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.0510. Min Act: -0.1700
Data Index: 4657043 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.0197. Min Act: -0.1700
Data Index: 2614165 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.0510. Min Act: -0.1700
Data Index: 4657044 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.0822. Min Act: -0.1700
Data Index: 8262742 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.0510. Min Act: -0.1700
Data Index: 7322981 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4572. Min Range: -4.4572
Max Act: 4.0197. Min Act: -0.1700
Data Index: 8366249 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19