Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.2185. Min Act: -0.1700
Data Index: 4669110 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.2185. Min Act: -0.1700
Data Index: 1858485 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.1873. Min Act: -0.1700
Data Index: 5331498 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.1248. Min Act: -0.1700
Data Index: 4222104 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.1248. Min Act: -0.1700
Data Index: 2314386 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.0935. Min Act: -0.1700
Data Index: 8682951 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.0623. Min Act: -0.1700
Data Index: 8205849 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.0310. Min Act: -0.1700
Data Index: 283063 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2185. Min Range: -5.2185
Max Act: 5.0310. Min Act: -0.1700
Data Index: 2223544 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9998. Min Act: -0.1700
Data Index: 4654066 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9685. Min Act: -0.1700
Data Index: 4919180 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9998. Min Act: -0.1700
Data Index: 26854 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9685. Min Act: -0.1700
Data Index: 2127156 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9998. Min Act: -0.1700
Data Index: 8598140 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9373. Min Act: -0.1700
Data Index: 1183194 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9373. Min Act: -0.1700
Data Index: 4919183 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9373. Min Act: -0.1700
Data Index: 2083309 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9373. Min Act: -0.1700
Data Index: 1905035 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9373. Min Act: -0.1700
Data Index: 1342125 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2185. Min Range: -5.2185
Max Act: 4.9060. Min Act: -0.1700
Data Index: 3098797 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19