Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4139 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.4635. Min Act: -0.1700
Data Index: 813201 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.1823. Min Act: -0.1700
Data Index: 3714077 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.1198. Min Act: -0.1700
Data Index: 3714073 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.0885. Min Act: -0.1700
Data Index: 1506888 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4635. Min Range: -7.4635
Max Act: 7.0573. Min Act: -0.1700
Data Index: 5511194 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9635. Min Act: -0.1700
Data Index: 5988353 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9948. Min Act: -0.1700
Data Index: 94343 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9948. Min Act: -0.1700
Data Index: 1286744 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9948. Min Act: -0.1700
Data Index: 3325519 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9635. Min Act: -0.1700
Data Index: 5520338 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9323. Min Act: -0.1700
Data Index: 2708496 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9323. Min Act: -0.1700
Data Index: 3450950 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9635. Min Act: -0.1700
Data Index: 1981664 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9010. Min Act: -0.1700
Data Index: 6647266 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9323. Min Act: -0.1700
Data Index: 6722407 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9010. Min Act: -0.1700
Data Index: 3714065 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.8385. Min Act: -0.1700
Data Index: 4939653 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.8698. Min Act: -0.1700
Data Index: 6530629 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.9010. Min Act: -0.1700
Data Index: 3006070 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4635. Min Range: -7.4635
Max Act: 6.8698. Min Act: -0.1700
Data Index: 2000530 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19