Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3404 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.1548. Min Range: -3.1548
Max Act: 3.1548. Min Act: -0.0001
Data Index: 1116440 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.4079. Min Act: -0.0001
Data Index: 587793 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.4877. Min Act: -0.0001
Data Index: 216555 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.3921. Min Act: -0.0001
Data Index: 141061 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.3471. Min Act: -0.0001
Data Index: 1265389 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.1625. Min Act: -0.0001
Data Index: 603179 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.2770. Min Act: -0.0001
Data Index: 883244 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.2578. Min Act: -0.0001
Data Index: 242846 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.2573. Min Act: -0.0001
Data Index: 967260 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.2138. Min Act: -0.0001
Data Index: 1067243 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.1962. Min Act: -0.0001
Data Index: 473467 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.3147. Min Act: -0.0001
Data Index: 958164 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.2016. Min Act: -0.0001
Data Index: 903564 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.1622. Min Act: -0.0001
Data Index: 638195 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.1474. Min Act: -0.0001
Data Index: 118946 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.0299. Min Act: -0.0001
Data Index: 457394 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.0218. Min Act: -0.0001
Data Index: 1157561 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.0050. Min Act: -0.0001
Data Index: 113350 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1548. Min Range: -3.1548
Max Act: 2.1017. Min Act: -0.0001
Data Index: 640669 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1548. Min Range: -3.1548
Max Act: 1.9855. Min Act: -0.0001
Data Index: 1313786 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19