Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 126 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.2006. Min Act: -0.1700
Data Index: 7196657 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.1693. Min Act: -0.1700
Data Index: 4571459 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.1068. Min Act: -0.1700
Data Index: 1880382 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.1068. Min Act: -0.1700
Data Index: 4135720 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.0130. Min Act: -0.1700
Data Index: 8814809 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.0130. Min Act: -0.1700
Data Index: 7439455 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.0443. Min Act: -0.1700
Data Index: 5846122 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.0130. Min Act: -0.1700
Data Index: 8826072 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9505. Min Act: -0.1700
Data Index: 4314321 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9818. Min Act: -0.1700
Data Index: 2001462 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9818. Min Act: -0.1700
Data Index: 1732652 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2006. Min Range: -4.2006
Max Act: 4.0130. Min Act: -0.1700
Data Index: 7277218 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9818. Min Act: -0.1700
Data Index: 6290280 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9505. Min Act: -0.1700
Data Index: 4409437 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9505. Min Act: -0.1700
Data Index: 4091054 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9505. Min Act: -0.1700
Data Index: 4612691 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9349. Min Act: -0.1700
Data Index: 3240761 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9192. Min Act: -0.1700
Data Index: 1919152 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9192. Min Act: -0.1700
Data Index: 1496265 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2006. Min Range: -4.2006
Max Act: 3.9192. Min Act: -0.1700
Data Index: 7663284 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19