Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2022 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.7131. Min Act: -0.0001
Data Index: 1334315 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.2861. Min Act: -0.0001
Data Index: 1065479 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.3545. Min Act: -0.0001
Data Index: 694219 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.3083. Min Act: -0.0001
Data Index: 275719 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.1309. Min Act: -0.0001
Data Index: 373263 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.2415. Min Act: -0.0001
Data Index: 955978 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.1708. Min Act: -0.0001
Data Index: 220997 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.2108. Min Act: -0.0001
Data Index: 1037788 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.9025. Min Act: -0.0001
Data Index: 198782 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.0401. Min Act: -0.0001
Data Index: 662813 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.9370. Min Act: -0.0001
Data Index: 1339601 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.9926. Min Act: -0.0001
Data Index: 1214272 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.0843. Min Act: -0.0001
Data Index: 1283377 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.9174. Min Act: -0.0001
Data Index: 528140 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.9618. Min Act: -0.0001
Data Index: 613515 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.9895. Min Act: -0.0001
Data Index: 656893 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.8693. Min Act: -0.0001
Data Index: 1207019 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.8544. Min Act: -0.0001
Data Index: 1113107 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7131. Min Range: -2.7131
Max Act: 2.0114. Min Act: -0.0001
Data Index: 1271184 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7131. Min Range: -2.7131
Max Act: 1.7482. Min Act: -0.0001
Data Index: 360408 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19