Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1284. Min Range: -4.1284
Max Act: 4.1284. Min Act: -0.1700
Data Index: 279776 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1284. Min Range: -4.1284
Max Act: 4.0658. Min Act: -0.1700
Data Index: 7134582 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1284. Min Range: -4.1284
Max Act: 4.0346. Min Act: -0.1700
Data Index: 4933426 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1284. Min Range: -4.1284
Max Act: 4.0346. Min Act: -0.1700
Data Index: 487069 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1284. Min Range: -4.1284
Max Act: 4.0033. Min Act: -0.1700
Data Index: 7542869 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.9721. Min Act: -0.1700
Data Index: 2807426 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.9408. Min Act: -0.1697
Data Index: 5784179 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.9408. Min Act: -0.1699
Data Index: 7238842 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.9095. Min Act: -0.1700
Data Index: 3382551 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.9408. Min Act: -0.1700
Data Index: 2216201 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.9408. Min Act: -0.1700
Data Index: 3449997 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.9408. Min Act: -0.1700
Data Index: 4188434 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.9095. Min Act: -0.1700
Data Index: 2671411 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.8470. Min Act: -0.1700
Data Index: 2526285 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.8783. Min Act: -0.1700
Data Index: 2438006 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.8783. Min Act: -0.1700
Data Index: 2911116 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.8783. Min Act: -0.1700
Data Index: 6777683 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.8470. Min Act: -0.1700
Data Index: 2198013 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.8470. Min Act: -0.1700
Data Index: 3965219 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1284. Min Range: -4.1284
Max Act: 3.7845. Min Act: -0.1700
Data Index: 2561564 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19