Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3303 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.8716. Min Act: -0.0001
Data Index: 628924 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.9173. Min Act: -0.0001
Data Index: 410317 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.6647. Min Act: -0.0001
Data Index: 513141 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.6402. Min Act: -0.0001
Data Index: 42447 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.5749. Min Act: -0.0001
Data Index: 1081799 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.4931. Min Act: -0.0001
Data Index: 1271077 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.5288. Min Act: -0.0001
Data Index: 721446 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.2535. Min Act: -0.0001
Data Index: 450331 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.3949. Min Act: -0.0001
Data Index: 1176071 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.3470. Min Act: -0.0001
Data Index: 660046 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.4651. Min Act: -0.0001
Data Index: 786060 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.4407. Min Act: -0.0001
Data Index: 330627 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.3251. Min Act: -0.0001
Data Index: 1070370 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.3158. Min Act: -0.0001
Data Index: 185026 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.1756. Min Act: -0.0001
Data Index: 85766 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.1712. Min Act: -0.0001
Data Index: 585177 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.1448. Min Act: -0.0001
Data Index: 831829 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.2580. Min Act: -0.0001
Data Index: 59733 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.3491. Min Act: -0.0001
Data Index: 978602 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9173. Min Range: -2.9173
Max Act: 2.1235. Min Act: -0.0001
Data Index: 1247920 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19