Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.7395. Min Act: -0.1700
Data Index: 5509252 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.6457. Min Act: -0.1700
Data Index: 2077526 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.5831. Min Act: -0.1700
Data Index: 5692030 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.5517. Min Act: -0.1700
Data Index: 2150095 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.5361. Min Act: -0.1700
Data Index: 2387880 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.5361. Min Act: -0.1700
Data Index: 5563394 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.5361. Min Act: -0.1700
Data Index: 7446503 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4891. Min Act: -0.1700
Data Index: 5853068 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4734. Min Act: -0.1700
Data Index: 3468846 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4421. Min Act: -0.1700
Data Index: 7268935 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4578. Min Act: -0.1700
Data Index: 8009401 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4578. Min Act: -0.1700
Data Index: 5036874 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4421. Min Act: -0.1700
Data Index: 6681810 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4108. Min Act: -0.1700
Data Index: 4929723 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4264. Min Act: -0.1700
Data Index: 7255000 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4264. Min Act: -0.1700
Data Index: 781791 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.4264. Min Act: -0.1700
Data Index: 3856864 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.3794. Min Act: -0.1700
Data Index: 7590660 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.3951. Min Act: -0.1700
Data Index: 4787133 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7395. Min Range: -3.7395
Max Act: 3.3794. Min Act: -0.1700
Data Index: 365358 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19