Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6037 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.4388. Min Act: -0.1700
Data Index: 891704 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.4076. Min Act: -0.1700
Data Index: 441829 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.4076. Min Act: -0.1700
Data Index: 8298301 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.4076. Min Act: -0.1700
Data Index: 6029554 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.3763. Min Act: -0.1700
Data Index: 1745593 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.3451. Min Act: -0.1700
Data Index: 8046744 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.3451. Min Act: -0.1700
Data Index: 6790474 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.3138. Min Act: -0.1700
Data Index: 3597907 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.3138. Min Act: -0.1700
Data Index: 7934165 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.3138. Min Act: -0.1700
Data Index: 5062135 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.3138. Min Act: -0.1700
Data Index: 5831423 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2826. Min Act: -0.1700
Data Index: 7557850 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2826. Min Act: -0.1700
Data Index: 5325099 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2826. Min Act: -0.1700
Data Index: 8321438 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2826. Min Act: -0.1700
Data Index: 6809895 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2826. Min Act: -0.1700
Data Index: 6041957 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2826. Min Act: -0.1700
Data Index: 8239438 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2513. Min Act: -0.1700
Data Index: 1347796 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2513. Min Act: -0.1700
Data Index: 7588816 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4388. Min Range: -4.4388
Max Act: 4.2513. Min Act: -0.1700
Data Index: 7909090 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19