Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 63 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.7726. Min Act: -0.1700
Data Index: 175134 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.7101. Min Act: -0.1700
Data Index: 3587198 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.5851. Min Act: -0.1700
Data Index: 6092032 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.4914. Min Act: -0.1700
Data Index: 4151913 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.4601. Min Act: -0.1700
Data Index: 8041883 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.4601. Min Act: -0.1700
Data Index: 5407193 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.4289. Min Act: -0.1700
Data Index: 4812918 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.4289. Min Act: -0.1700
Data Index: 4775900 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.3976. Min Act: -0.1700
Data Index: 2371076 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.3351. Min Act: -0.1700
Data Index: 3748116 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.3351. Min Act: -0.1700
Data Index: 862395 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.3039. Min Act: -0.1700
Data Index: 2562458 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.3039. Min Act: -0.1700
Data Index: 679505 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.3039. Min Act: -0.1700
Data Index: 337881 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.3039. Min Act: -0.1700
Data Index: 2617329 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.2726. Min Act: -0.1700
Data Index: 7760407 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.2726. Min Act: -0.1700
Data Index: 809058 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.2726. Min Act: -0.1700
Data Index: 6181660 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.2414. Min Act: -0.1700
Data Index: 3565128 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7726. Min Range: -6.7726
Max Act: 6.2414. Min Act: -0.1700
Data Index: 4248248 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19