Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.1494. Min Act: -0.1700
Data Index: 4377629 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.1651. Min Act: -0.1700
Data Index: 8016721 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.1179. Min Act: -0.1700
Data Index: 7802201 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.1021. Min Act: -0.1700
Data Index: 3992381 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0864. Min Act: -0.1700
Data Index: 1907069 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.1021. Min Act: -0.1700
Data Index: 1955977 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0864. Min Act: -0.1700
Data Index: 1701399 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0548. Min Act: -0.1700
Data Index: 1482189 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0706. Min Act: -0.1700
Data Index: 2140735 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0391. Min Act: -0.1700
Data Index: 4399551 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0233. Min Act: -0.1700
Data Index: 840218 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0233. Min Act: -0.1700
Data Index: 3120768 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0391. Min Act: -0.1700
Data Index: 2005880 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1651. Min Range: -3.1651
Max Act: 2.9917. Min Act: -0.1700
Data Index: 840224 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1651. Min Range: -3.1651
Max Act: 2.9600. Min Act: -0.1700
Data Index: 2309645 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1651. Min Range: -3.1651
Max Act: 2.9917. Min Act: -0.1700
Data Index: 1942480 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1651. Min Range: -3.1651
Max Act: 2.9759. Min Act: -0.1700
Data Index: 1775155 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1651. Min Range: -3.1651
Max Act: 2.9600. Min Act: -0.1700
Data Index: 7099990 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1651. Min Range: -3.1651
Max Act: 2.9917. Min Act: -0.1700
Data Index: 4493945 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1651. Min Range: -3.1651
Max Act: 3.0075. Min Act: -0.1700
Data Index: 6943464 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19