Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 766 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.9714. Min Act: -0.1700
Data Index: 6681840 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.9089. Min Act: -0.1700
Data Index: 6510137 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.7839. Min Act: -0.1700
Data Index: 1317333 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.7839. Min Act: -0.1700
Data Index: 5947720 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5964. Min Act: -0.1700
Data Index: 6373705 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.6276. Min Act: -0.1700
Data Index: 5708409 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5651. Min Act: -0.1700
Data Index: 7825269 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5651. Min Act: -0.1700
Data Index: 3981965 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5651. Min Act: -0.1700
Data Index: 3435571 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5339. Min Act: -0.1700
Data Index: 80317 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5339. Min Act: -0.1700
Data Index: 6419061 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5339. Min Act: -0.1700
Data Index: 5363694 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5339. Min Act: -0.1700
Data Index: 2353748 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.5026. Min Act: -0.1700
Data Index: 6118720 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 1519724 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.4401. Min Act: -0.1700
Data Index: 4853185 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.4401. Min Act: -0.1700
Data Index: 3347854 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.4401. Min Act: -0.1700
Data Index: 8496703 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.4401. Min Act: -0.1700
Data Index: 4181521 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9714. Min Range: -7.9714
Max Act: 7.4089. Min Act: -0.1700
Data Index: 4833689 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19