Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.5265. Min Act: -0.1700
Data Index: 3937612 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.5108. Min Act: -0.1700
Data Index: 8127394 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.4795. Min Act: -0.1700
Data Index: 2421061 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.4638. Min Act: -0.1700
Data Index: 3562011 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.4168. Min Act: -0.1700
Data Index: 3225264 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.4168. Min Act: -0.1700
Data Index: 4967814 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.4011. Min Act: -0.1700
Data Index: 4926935 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.4011. Min Act: -0.1700
Data Index: 2847693 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.3855. Min Act: -0.1700
Data Index: 5115438 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.3541. Min Act: -0.1700
Data Index: 2845161 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2913. Min Act: -0.1700
Data Index: 109993 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2756. Min Act: -0.1700
Data Index: 5741626 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2756. Min Act: -0.1700
Data Index: 6985233 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2756. Min Act: -0.1700
Data Index: 54065 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2599. Min Act: -0.1700
Data Index: 5912354 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2599. Min Act: -0.1700
Data Index: 2098864 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2442. Min Act: -0.1700
Data Index: 2508754 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2442. Min Act: -0.1700
Data Index: 6499262 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2442. Min Act: -0.1700
Data Index: 3965843 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5265. Min Range: -3.5265
Max Act: 3.2442. Min Act: -0.1700
Data Index: 4056585 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19