Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5296 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1302. Min Range: -7.1302
Max Act: 7.1302. Min Act: -0.1700
Data Index: 1870833 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1302. Min Range: -7.1302
Max Act: 7.0052. Min Act: -0.1700
Data Index: 3345719 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.9114. Min Act: -0.1700
Data Index: 1917248 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.8177. Min Act: -0.1700
Data Index: 5007479 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.7239. Min Act: -0.1700
Data Index: 6768522 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.6927. Min Act: -0.1700
Data Index: 4161199 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.6927. Min Act: -0.1700
Data Index: 6768527 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.6927. Min Act: -0.1700
Data Index: 2613160 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.6927. Min Act: -0.1700
Data Index: 6125781 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.6614. Min Act: -0.1700
Data Index: 1276303 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.6302. Min Act: -0.1700
Data Index: 4581332 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.6302. Min Act: -0.1700
Data Index: 6664038 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.6302. Min Act: -0.1700
Data Index: 8007535 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.5989. Min Act: -0.1700
Data Index: 5113660 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.5677. Min Act: -0.1700
Data Index: 7889156 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.5677. Min Act: -0.1700
Data Index: 1984275 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.5677. Min Act: -0.1700
Data Index: 3067731 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.5364. Min Act: -0.1700
Data Index: 2019741 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.5364. Min Act: -0.1700
Data Index: 4363568 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1302. Min Range: -7.1302
Max Act: 6.5364. Min Act: -0.1700
Data Index: 1656219 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19