Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4421 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.7584. Min Act: -0.1700
Data Index: 5131208 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.7584. Min Act: -0.1700
Data Index: 686440 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.6334. Min Act: -0.1700
Data Index: 3787695 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.5084. Min Act: -0.1700
Data Index: 315445 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.4772. Min Act: -0.1700
Data Index: 3586418 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.3522. Min Act: -0.1700
Data Index: 8322758 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.3209. Min Act: -0.1700
Data Index: 2616731 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2584. Min Act: -0.1700
Data Index: 4461302 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2584. Min Act: -0.1700
Data Index: 133035 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2584. Min Act: -0.1700
Data Index: 2662183 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2584. Min Act: -0.1700
Data Index: 6280982 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2584. Min Act: -0.1700
Data Index: 3100454 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2272. Min Act: -0.1700
Data Index: 6371609 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2272. Min Act: -0.1700
Data Index: 4184471 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2272. Min Act: -0.1700
Data Index: 2816045 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.2272. Min Act: -0.1700
Data Index: 7564330 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.1959. Min Act: -0.1700
Data Index: 251616 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.1959. Min Act: -0.1700
Data Index: 6425057 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.1959. Min Act: -0.1700
Data Index: 8496893 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7584. Min Range: -4.7584
Max Act: 4.1646. Min Act: -0.1700
Data Index: 2425455 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19