Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.7478. Min Act: -0.1700
Data Index: 7060099 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.6785. Min Act: -0.1700
Data Index: 8555561 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.6350. Min Act: -0.1700
Data Index: 2898542 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.6001. Min Act: -0.1700
Data Index: 4920697 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5827. Min Act: -0.1700
Data Index: 4861757 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.6001. Min Act: -0.1700
Data Index: 8770991 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5827. Min Act: -0.1700
Data Index: 4300205 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5827. Min Act: -0.1700
Data Index: 6303635 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5827. Min Act: -0.1700
Data Index: 6887171 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5652. Min Act: -0.1700
Data Index: 3823566 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5564. Min Act: -0.1700
Data Index: 140207 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5564. Min Act: -0.1700
Data Index: 7788550 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5564. Min Act: -0.1700
Data Index: 8551116 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5564. Min Act: -0.1700
Data Index: 4714080 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5477. Min Act: -0.1699
Data Index: 2073511 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5389. Min Act: -0.1699
Data Index: 6724338 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5389. Min Act: -0.1700
Data Index: 5960172 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5389. Min Act: -0.1700
Data Index: 6174351 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5389. Min Act: -0.1700
Data Index: 905316 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7478. Min Range: -1.7478
Max Act: 1.5389. Min Act: -0.1700
Data Index: 6287283 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19