Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4078 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2512. Min Range: -8.2512
Max Act: 8.1887. Min Act: -0.1700
Data Index: 7514320 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2512. Min Range: -8.2512
Max Act: 8.2512. Min Act: -0.1700
Data Index: 1466667 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2512. Min Range: -8.2512
Max Act: 8.1887. Min Act: -0.1700
Data Index: 6797637 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2512. Min Range: -8.2512
Max Act: 8.0012. Min Act: -0.1700
Data Index: 5201237 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2512. Min Range: -8.2512
Max Act: 8.0012. Min Act: -0.1700
Data Index: 8080908 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2512. Min Range: -8.2512
Max Act: 8.0012. Min Act: -0.1700
Data Index: 4610972 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.8762. Min Act: -0.1700
Data Index: 1478761 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.8137. Min Act: -0.1700
Data Index: 5214111 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.4699. Min Act: -0.1700
Data Index: 3315453 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.4074. Min Act: -0.1700
Data Index: 8109072 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.5012. Min Act: -0.1700
Data Index: 300089 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.3762. Min Act: -0.1700
Data Index: 716240 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.3137. Min Act: -0.1700
Data Index: 2633034 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.3449. Min Act: -0.1700
Data Index: 6517872 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.3137. Min Act: -0.1700
Data Index: 3459214 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.3449. Min Act: -0.1700
Data Index: 4662463 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.1887. Min Act: -0.1700
Data Index: 3384925 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.2199. Min Act: -0.1700
Data Index: 5229642 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.1574. Min Act: -0.1700
Data Index: 8652806 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2512. Min Range: -8.2512
Max Act: 7.1262. Min Act: -0.1700
Data Index: 3157889 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19