Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.9308. Min Act: -0.1700
Data Index: 8172638 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.9308. Min Act: -0.1700
Data Index: 5721581 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.9149. Min Act: -0.1700
Data Index: 8787677 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8991. Min Act: -0.1700
Data Index: 3095550 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.9149. Min Act: -0.1700
Data Index: 5799233 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8991. Min Act: -0.1700
Data Index: 274610 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8991. Min Act: -0.1700
Data Index: 785658 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8832. Min Act: -0.1700
Data Index: 2229815 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8515. Min Act: -0.1700
Data Index: 4309093 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8515. Min Act: -0.1700
Data Index: 3880646 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8356. Min Act: -0.1700
Data Index: 7239926 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8197. Min Act: -0.1700
Data Index: 5821289 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8197. Min Act: -0.1700
Data Index: 8728622 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8197. Min Act: -0.1700
Data Index: 3282841 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8197. Min Act: -0.1700
Data Index: 6469534 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8037. Min Act: -0.1700
Data Index: 1018419 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8197. Min Act: -0.1700
Data Index: 6969139 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.7878. Min Act: -0.1700
Data Index: 3868692 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8037. Min Act: -0.1700
Data Index: 1924340 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9308. Min Range: -2.9308
Max Act: 2.8037. Min Act: -0.1700
Data Index: 6535459 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19