Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1165 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.4850. Min Act: -0.1700
Data Index: 7000665 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.4850. Min Act: -0.1700
Data Index: 1097698 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.4225. Min Act: -0.1700
Data Index: 5887498 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.4225. Min Act: -0.1700
Data Index: 6563031 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.3913. Min Act: -0.1700
Data Index: 5568671 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.3288. Min Act: -0.1700
Data Index: 4402078 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.3288. Min Act: -0.1700
Data Index: 5636393 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2975. Min Act: -0.1700
Data Index: 2645508 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.3288. Min Act: -0.1700
Data Index: 6107307 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.3600. Min Act: -0.1700
Data Index: 4183005 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2975. Min Act: -0.1700
Data Index: 4140870 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2975. Min Act: -0.1700
Data Index: 6223521 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2662. Min Act: -0.1700
Data Index: 1848083 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2662. Min Act: -0.1700
Data Index: 4475485 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2975. Min Act: -0.1700
Data Index: 4358596 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2662. Min Act: -0.1700
Data Index: 223107 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2662. Min Act: -0.1700
Data Index: 3543230 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2350. Min Act: -0.1700
Data Index: 5943485 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2350. Min Act: -0.1700
Data Index: 722735 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4850. Min Range: -4.4850
Max Act: 4.2350. Min Act: -0.1700
Data Index: 123326 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19