Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.5472. Min Act: -0.1700
Data Index: 4865297 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4847. Min Act: -0.1700
Data Index: 1451829 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3909. Min Act: -0.1700
Data Index: 2364725 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4222. Min Act: -0.1700
Data Index: 8727239 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.4222. Min Act: -0.1700
Data Index: 5833920 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3597. Min Act: -0.1700
Data Index: 5326384 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3597. Min Act: -0.1700
Data Index: 5385567 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3284. Min Act: -0.1700
Data Index: 7801620 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3284. Min Act: -0.1700
Data Index: 8275348 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3284. Min Act: -0.1700
Data Index: 937026 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3284. Min Act: -0.1700
Data Index: 6034815 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3284. Min Act: -0.1700
Data Index: 1315120 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2971. Min Act: -0.1700
Data Index: 6056118 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 4375305 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2971. Min Act: -0.1700
Data Index: 6179611 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2971. Min Act: -0.1700
Data Index: 6580521 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 1617280 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 4796808 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2971. Min Act: -0.1700
Data Index: 4091684 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2659. Min Act: -0.1700
Data Index: 7982541 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19