Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1842 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.2968. Min Range: -4.2968
Max Act: 4.2968. Min Act: -0.0001
Data Index: 336210 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.9760. Min Act: -0.0001
Data Index: 772260 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.7422. Min Act: -0.0001
Data Index: 437608 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.2820. Min Act: -0.0001
Data Index: 91890 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.3522. Min Act: -0.0001
Data Index: 1348660 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.2814. Min Act: -0.0001
Data Index: 1013112 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.6231. Min Act: -0.0001
Data Index: 827073 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.4388. Min Act: -0.0001
Data Index: 1300555 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.6889. Min Act: -0.0001
Data Index: 646080 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.3689. Min Act: -0.0001
Data Index: 874318 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.3601. Min Act: -0.0001
Data Index: 560828 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.5325. Min Act: -0.0001
Data Index: 224583 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.2199. Min Act: -0.0001
Data Index: 1191712 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.6784. Min Act: -0.0001
Data Index: 539919 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.0014. Min Act: -0.0001
Data Index: 1275420 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2968. Min Range: -4.2968
Max Act: 3.2332. Min Act: -0.0001
Data Index: 1140460 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2968. Min Range: -4.2968
Max Act: 2.6440. Min Act: -0.0001
Data Index: 512700 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2968. Min Range: -4.2968
Max Act: 2.8181. Min Act: -0.0001
Data Index: 127493 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2968. Min Range: -4.2968
Max Act: 2.8158. Min Act: -0.0001
Data Index: 1074957 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2968. Min Range: -4.2968
Max Act: 2.7476. Min Act: -0.0001
Data Index: 1015392 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19