Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2965 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.5266. Min Range: -3.5266
Max Act: 3.5266. Min Act: -0.0001
Data Index: 795834 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5266. Min Range: -3.5266
Max Act: 3.1611. Min Act: -0.0000
Data Index: 1111609 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5266. Min Range: -3.5266
Max Act: 3.0371. Min Act: 0.0000
Data Index: 525139 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5266. Min Range: -3.5266
Max Act: 3.1619. Min Act: -0.0001
Data Index: 979683 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.6029. Min Act: -0.0001
Data Index: 678063 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.8268. Min Act: -0.0001
Data Index: 800390 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.6884. Min Act: -0.0001
Data Index: 93886 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.7831. Min Act: -0.0001
Data Index: 147217 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.4890. Min Act: -0.0001
Data Index: 22375 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.4900. Min Act: -0.0001
Data Index: 723303 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.4934. Min Act: -0.0001
Data Index: 1346297 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.6235. Min Act: -0.0001
Data Index: 122599 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.3698. Min Act: -0.0001
Data Index: 84828 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.4916. Min Act: -0.0001
Data Index: 325491 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.4620. Min Act: -0.0001
Data Index: 109881 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.4364. Min Act: -0.0001
Data Index: 1070886 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.4179. Min Act: -0.0001
Data Index: 762041 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.5546. Min Act: -0.0001
Data Index: 1141998 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.2663. Min Act: -0.0001
Data Index: 1176459 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5266. Min Range: -3.5266
Max Act: 2.3824. Min Act: -0.0001
Data Index: 804691 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19