Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3857 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.7546. Min Act: -0.1700
Data Index: 463965 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.6921. Min Act: -0.1700
Data Index: 5192393 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.5983. Min Act: -0.1700
Data Index: 5192391 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.5671. Min Act: -0.1700
Data Index: 3931189 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.5671. Min Act: -0.1700
Data Index: 1713420 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.5358. Min Act: -0.1700
Data Index: 7893004 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.5358. Min Act: -0.1700
Data Index: 7236581 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.5046. Min Act: -0.1700
Data Index: 8552616 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.5358. Min Act: -0.1700
Data Index: 7778581 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4733. Min Act: -0.1700
Data Index: 6191837 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4733. Min Act: -0.1700
Data Index: 2015009 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4421. Min Act: -0.1700
Data Index: 6559427 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4421. Min Act: -0.1700
Data Index: 7358883 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4733. Min Act: -0.1700
Data Index: 4085608 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4421. Min Act: -0.1700
Data Index: 3955856 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4421. Min Act: -0.1700
Data Index: 1401066 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4108. Min Act: -0.1700
Data Index: 4236948 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.3796. Min Act: -0.1700
Data Index: 2834953 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4108. Min Act: -0.1700
Data Index: 2693723 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7546. Min Range: -5.7546
Max Act: 5.4108. Min Act: -0.1700
Data Index: 4434539 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19