Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.6085. Min Act: -0.1700
Data Index: 7683192 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.6398. Min Act: -0.1700
Data Index: 4187559 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.6085. Min Act: -0.1700
Data Index: 3482210 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.5460. Min Act: -0.1700
Data Index: 6524955 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.5460. Min Act: -0.1700
Data Index: 4340912 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.5460. Min Act: -0.1700
Data Index: 2698474 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.5148. Min Act: -0.1700
Data Index: 850681 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.4835. Min Act: -0.1700
Data Index: 3758875 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.4523. Min Act: -0.1700
Data Index: 646537 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.4210. Min Act: -0.1700
Data Index: 5538868 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.4210. Min Act: -0.1700
Data Index: 8279387 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.3585. Min Act: -0.1700
Data Index: 6312843 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.3585. Min Act: -0.1700
Data Index: 3864011 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.3273. Min Act: -0.1700
Data Index: 2591512 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.2648. Min Act: -0.1700
Data Index: 1593490 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.2648. Min Act: -0.1700
Data Index: 1995916 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.2335. Min Act: -0.1700
Data Index: 3741185 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.1710. Min Act: -0.1700
Data Index: 1545315 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.1710. Min Act: -0.1700
Data Index: 5680937 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6398. Min Range: -5.6398
Max Act: 5.1398. Min Act: -0.1700
Data Index: 7284801 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19