Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2643 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3835. Min Range: -2.3835
Max Act: 2.3835. Min Act: -0.0001
Data Index: 292380 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3835. Min Range: -2.3835
Max Act: 2.1479. Min Act: -0.0001
Data Index: 628860 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3835. Min Range: -2.3835
Max Act: 2.1833. Min Act: -0.0001
Data Index: 466365 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.9464. Min Act: -0.0001
Data Index: 227753 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.8758. Min Act: -0.0001
Data Index: 672364 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.7540. Min Act: -0.0001
Data Index: 321048 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.8631. Min Act: -0.0001
Data Index: 1087385 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.7424. Min Act: -0.0001
Data Index: 1301935 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.4386. Min Act: -0.0001
Data Index: 362805 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.3912. Min Act: -0.0001
Data Index: 1126009 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.5540. Min Act: -0.0000
Data Index: 1210619 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.5077. Min Act: -0.0001
Data Index: 768778 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.5365. Min Act: -0.0001
Data Index: 1085130 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.6047. Min Act: -0.0001
Data Index: 716168 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.4983. Min Act: -0.0001
Data Index: 1055075 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.3558. Min Act: -0.0001
Data Index: 902040 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.4575. Min Act: -0.0001
Data Index: 1189637 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.2071. Min Act: -0.0001
Data Index: 668302 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.4257. Min Act: -0.0001
Data Index: 838217 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3835. Min Range: -2.3835
Max Act: 1.2809. Min Act: -0.0001
Data Index: 498861 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19