Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2949 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.6108. Min Act: -0.0001
Data Index: 683531 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.6254. Min Act: -0.0001
Data Index: 100920 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.4153. Min Act: -0.0001
Data Index: 479492 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.5139. Min Act: -0.0001
Data Index: 1240441 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.4245. Min Act: -0.0001
Data Index: 485628 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.4002. Min Act: -0.0001
Data Index: 732943 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.4919. Min Act: -0.0001
Data Index: 771000 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.3818. Min Act: -0.0001
Data Index: 329032 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.2598. Min Act: -0.0001
Data Index: 40360 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.5844. Min Act: -0.0001
Data Index: 1062947 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.3025. Min Act: -0.0001
Data Index: 631953 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.1511. Min Act: -0.0001
Data Index: 1163662 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.3394. Min Act: -0.0001
Data Index: 150511 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6254. Min Range: -2.6254
Max Act: 1.9466. Min Act: -0.0001
Data Index: 1356532 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.1790. Min Act: -0.0001
Data Index: 910887 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.1789. Min Act: -0.0001
Data Index: 1284145 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.1729. Min Act: -0.0001
Data Index: 1125345 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.1728. Min Act: -0.0001
Data Index: 289620 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.1325. Min Act: -0.0001
Data Index: 1278850 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6254. Min Range: -2.6254
Max Act: 2.0252. Min Act: -0.0001
Data Index: 452372 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19