Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2354 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.4721. Min Act: -0.0001
Data Index: 682532 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3910. Min Act: -0.0001
Data Index: 1425128 (Python Code)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.2897. Min Act: -0.0001
Data Index: 523837 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3131. Min Act: -0.0001
Data Index: 776822 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3193. Min Act: -0.0001
Data Index: 1394318 (Python Code)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.2194. Min Act: -0.0001
Data Index: 1211890 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3888. Min Act: -0.0001
Data Index: 524464 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3360. Min Act: -0.0001
Data Index: 1378462 (Python Code)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.2671. Min Act: -0.0001
Data Index: 391073 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3241. Min Act: -0.0001
Data Index: 1148315 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.2598. Min Act: -0.0001
Data Index: 1580713 (Python Code)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3579. Min Act: -0.0001
Data Index: 1574406 (Python Code)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3595. Min Act: -0.0001
Data Index: 1624652 (Python Code)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.1991. Min Act: -0.0001
Data Index: 885403 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.2977. Min Act: -0.0001
Data Index: 289118 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.3374. Min Act: -0.0001
Data Index: 1654216 (Python Code)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.2214. Min Act: -0.0001
Data Index: 1634696 (Python Code)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.2290. Min Act: -0.0001
Data Index: 1553464 (Python Code)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.2810. Min Act: -0.0001
Data Index: 774203 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4721. Min Range: -1.4721
Max Act: 1.1215. Min Act: -0.0001
Data Index: 926300 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19