Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 517 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.3499. Min Act: -0.0001
Data Index: 153822 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.4469. Min Act: -0.0001
Data Index: 752333 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.4423. Min Act: -0.0001
Data Index: 28538 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.2204. Min Act: -0.0001
Data Index: 1178850 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.2129. Min Act: -0.0001
Data Index: 466112 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.3232. Min Act: -0.0001
Data Index: 1207936 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.3225. Min Act: -0.0001
Data Index: 663737 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.1191. Min Act: -0.0001
Data Index: 976313 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.4367. Min Act: -0.0001
Data Index: 906409 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.2970. Min Act: -0.0001
Data Index: 513901 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.2899. Min Act: -0.0001
Data Index: 513678 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.3511. Min Act: -0.0001
Data Index: 472699 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.2734. Min Act: -0.0001
Data Index: 1161457 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.3515. Min Act: -0.0001
Data Index: 114626 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.1034. Min Act: -0.0001
Data Index: 863655 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.0608. Min Act: -0.0001
Data Index: 1131210 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.1545. Min Act: -0.0001
Data Index: 1287077 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.2413. Min Act: -0.0001
Data Index: 1081248 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.2197. Min Act: -0.0001
Data Index: 283496 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4469. Min Range: -1.4469
Max Act: 1.2235. Min Act: -0.0001
Data Index: 978296 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19