Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2249 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.7669. Min Act: -0.1700
Data Index: 282206 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.7044. Min Act: -0.1700
Data Index: 2070443 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.6731. Min Act: -0.1700
Data Index: 8118764 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.6419. Min Act: -0.1700
Data Index: 7928231 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.6419. Min Act: -0.1700
Data Index: 4629502 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.5794. Min Act: -0.1700
Data Index: 5205116 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.5794. Min Act: -0.1700
Data Index: 2250851 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.5481. Min Act: -0.1700
Data Index: 7851804 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.5794. Min Act: -0.1700
Data Index: 8531010 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.5794. Min Act: -0.1700
Data Index: 7968786 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.5481. Min Act: -0.1700
Data Index: 7928230 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.5481. Min Act: -0.1700
Data Index: 1654484 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.4856. Min Act: -0.1700
Data Index: 4338310 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.4856. Min Act: -0.1700
Data Index: 5275951 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.4856. Min Act: -0.1700
Data Index: 2250853 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.4856. Min Act: -0.1700
Data Index: 8207181 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.5169. Min Act: -0.1700
Data Index: 1185143 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.4544. Min Act: -0.1700
Data Index: 5394219 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.4544. Min Act: -0.1700
Data Index: 6952192 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7669. Min Range: -5.7669
Max Act: 5.4544. Min Act: -0.1700
Data Index: 8146369 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19