Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 816 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.3737. Min Act: -0.1700
Data Index: 6212001 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.3425. Min Act: -0.1700
Data Index: 5727879 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.3112. Min Act: -0.1700
Data Index: 7480818 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2487. Min Act: -0.1700
Data Index: 6273947 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2487. Min Act: -0.1700
Data Index: 5439501 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2487. Min Act: -0.1700
Data Index: 4260530 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2487. Min Act: -0.1700
Data Index: 8686776 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2487. Min Act: -0.1700
Data Index: 4257558 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2487. Min Act: -0.1700
Data Index: 8247749 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2175. Min Act: -0.1700
Data Index: 7996349 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2175. Min Act: -0.1700
Data Index: 5718663 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2175. Min Act: -0.1700
Data Index: 2719055 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.1862. Min Act: -0.1700
Data Index: 6084485 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.1862. Min Act: -0.1700
Data Index: 3229055 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.2175. Min Act: -0.1700
Data Index: 7197175 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.1862. Min Act: -0.1700
Data Index: 2189944 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.1550. Min Act: -0.1700
Data Index: 7737670 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.1237. Min Act: -0.1700
Data Index: 576756 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.1237. Min Act: -0.1700
Data Index: 889360 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3737. Min Range: -5.3737
Max Act: 5.1237. Min Act: -0.1700
Data Index: 4158238 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19