Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1393 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2326. Min Act: -0.0001
Data Index: 1352959 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2315. Min Act: -0.0001
Data Index: 1423989 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2288. Min Act: -0.0001
Data Index: 551248 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2207. Min Act: -0.0001
Data Index: 429919 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2145. Min Act: -0.0001
Data Index: 1092386 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2034. Min Act: -0.0001
Data Index: 696055 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2015. Min Act: -0.0001
Data Index: 890210 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2078. Min Act: -0.0001
Data Index: 1549536 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.1944. Min Act: -0.0001
Data Index: 347831 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2061. Min Act: -0.0001
Data Index: 744476 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2040. Min Act: -0.0001
Data Index: 820708 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2039. Min Act: -0.0001
Data Index: 358417 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2013. Min Act: -0.0001
Data Index: 1058851 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2002. Min Act: -0.0001
Data Index: 956609 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.1990. Min Act: -0.0001
Data Index: 933643 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.1997. Min Act: -0.0001
Data Index: 93217 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.1917. Min Act: -0.0001
Data Index: 511575 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.1975. Min Act: -0.0001
Data Index: 870361 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.2018. Min Act: -0.0001
Data Index: 378661 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2326. Min Range: -0.2326
Max Act: 0.1875. Min Act: -0.0001
Data Index: 902265 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19