Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.7135. Min Act: -0.1700
Data Index: 6811123 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.6197. Min Act: -0.1700
Data Index: 7765603 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.5885. Min Act: -0.1700
Data Index: 1985271 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.5572. Min Act: -0.1700
Data Index: 7052367 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.5260. Min Act: -0.1700
Data Index: 7292281 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.5260. Min Act: -0.1700
Data Index: 515993 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.4947. Min Act: -0.1700
Data Index: 4587856 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.4947. Min Act: -0.1700
Data Index: 5565802 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.4322. Min Act: -0.1700
Data Index: 6444439 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.4010. Min Act: -0.1700
Data Index: 8300318 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.4010. Min Act: -0.1700
Data Index: 5768621 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3697. Min Act: -0.1700
Data Index: 6774613 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3697. Min Act: -0.1700
Data Index: 6472033 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3385. Min Act: -0.1700
Data Index: 37203 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3385. Min Act: -0.1700
Data Index: 6078787 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3385. Min Act: -0.1700
Data Index: 5348461 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3385. Min Act: -0.1700
Data Index: 441296 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3385. Min Act: -0.1700
Data Index: 1541289 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3385. Min Act: -0.1700
Data Index: 2784727 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7135. Min Range: -4.7135
Max Act: 4.3072. Min Act: -0.1700
Data Index: 4104837 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19