Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.5951. Min Act: -0.1700
Data Index: 1631778 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.4701. Min Act: -0.1700
Data Index: 3532687 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.4388. Min Act: -0.1700
Data Index: 326960 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.4388. Min Act: -0.1700
Data Index: 3228707 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3763. Min Act: -0.1700
Data Index: 4822465 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3450. Min Act: -0.1700
Data Index: 5759015 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3450. Min Act: -0.1700
Data Index: 1820165 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3450. Min Act: -0.1700
Data Index: 2148323 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3138. Min Act: -0.1700
Data Index: 8565962 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3138. Min Act: -0.1700
Data Index: 4882755 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3138. Min Act: -0.1700
Data Index: 3708486 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3138. Min Act: -0.1700
Data Index: 1199295 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.2825. Min Act: -0.1700
Data Index: 5117849 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.2825. Min Act: -0.1700
Data Index: 250594 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.3138. Min Act: -0.1700
Data Index: 5647236 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.2825. Min Act: -0.1700
Data Index: 7580651 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.2825. Min Act: -0.1700
Data Index: 2631952 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.2513. Min Act: -0.1700
Data Index: 1662995 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.2513. Min Act: -0.1700
Data Index: 8257866 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5951. Min Range: -4.5951
Max Act: 4.2513. Min Act: -0.1700
Data Index: 4822470 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19