Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2813 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.2410. Min Range: -15.2410
Max Act: 15.2410. Min Act: -0.1700
Data Index: 2233314 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.2410. Min Range: -15.2410
Max Act: 15.0535. Min Act: -0.1700
Data Index: 2694138 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.2410. Min Range: -15.2410
Max Act: 15.0535. Min Act: -0.1700
Data Index: 1798124 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.2410. Min Range: -15.2410
Max Act: 15.1160. Min Act: -0.1700
Data Index: 3332265 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.2410. Min Range: -15.2410
Max Act: 15.0535. Min Act: -0.1700
Data Index: 6386927 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.9910. Min Act: -0.1700
Data Index: 5361960 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.9285. Min Act: -0.1700
Data Index: 6765249 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.9285. Min Act: -0.1700
Data Index: 947233 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8660. Min Act: -0.1700
Data Index: 8269334 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8660. Min Act: -0.1700
Data Index: 5609792 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8035. Min Act: -0.1700
Data Index: 5182651 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8035. Min Act: -0.1700
Data Index: 8265124 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8035. Min Act: -0.1700
Data Index: 554028 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8035. Min Act: -0.1700
Data Index: 7359450 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8035. Min Act: -0.1700
Data Index: 3185617 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8035. Min Act: -0.1700
Data Index: 1970063 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8035. Min Act: -0.1700
Data Index: 2699057 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.8035. Min Act: -0.1700
Data Index: 4076956 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.7410. Min Act: -0.1700
Data Index: 6018105 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.2410. Min Range: -15.2410
Max Act: 14.7410. Min Act: -0.1700
Data Index: 7128931 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19