Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1911 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.5909. Min Act: -0.1700
Data Index: 5354664 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.2784. Min Act: -0.1700
Data Index: 5883971 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.2159. Min Act: -0.1700
Data Index: 2826054 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.2784. Min Act: -0.1700
Data Index: 4002664 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.2784. Min Act: -0.1700
Data Index: 335544 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.2159. Min Act: -0.1700
Data Index: 7667615 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.2159. Min Act: -0.1700
Data Index: 3585462 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.2159. Min Act: -0.1700
Data Index: 2184282 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.2159. Min Act: -0.1700
Data Index: 5729501 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0909. Min Act: -0.1700
Data Index: 4163581 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0284. Min Act: -0.1700
Data Index: 7026629 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0909. Min Act: -0.1700
Data Index: 1644392 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0909. Min Act: -0.1700
Data Index: 8526117 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0284. Min Act: -0.1700
Data Index: 547180 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0284. Min Act: -0.1700
Data Index: 5010639 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0284. Min Act: -0.1700
Data Index: 4558479 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0284. Min Act: -0.1700
Data Index: 2990801 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5909. Min Range: -9.5909
Max Act: 9.0284. Min Act: -0.1700
Data Index: 5630151 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5909. Min Range: -9.5909
Max Act: 8.9659. Min Act: -0.1700
Data Index: 1148059 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5909. Min Range: -9.5909
Max Act: 8.9659. Min Act: -0.1700
Data Index: 3568967 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19