Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.7655. Min Act: -0.1700
Data Index: 7076422 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.6093. Min Act: -0.1700
Data Index: 5492251 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.6405. Min Act: -0.1700
Data Index: 6842705 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.6093. Min Act: -0.1700
Data Index: 279462 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.5780. Min Act: -0.1700
Data Index: 2266755 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.6093. Min Act: -0.1700
Data Index: 591449 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.5155. Min Act: -0.1700
Data Index: 1613208 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.5155. Min Act: -0.1700
Data Index: 12184 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.5155. Min Act: -0.1700
Data Index: 4872609 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.5155. Min Act: -0.1700
Data Index: 4811823 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.4218. Min Act: -0.1700
Data Index: 7180962 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.4843. Min Act: -0.1700
Data Index: 2493105 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.4530. Min Act: -0.1700
Data Index: 5565645 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.3905. Min Act: -0.1700
Data Index: 486790 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.4218. Min Act: -0.1700
Data Index: 4562243 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.3905. Min Act: -0.1700
Data Index: 6631827 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.3593. Min Act: -0.1700
Data Index: 4409658 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.3905. Min Act: -0.1700
Data Index: 3028983 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.3905. Min Act: -0.1700
Data Index: 422963 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7655. Min Range: -6.7655
Max Act: 6.3593. Min Act: -0.1700
Data Index: 3820337 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19