Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3908 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1677. Min Range: -2.1677
Max Act: 2.1677. Min Act: -0.0001
Data Index: 500911 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.8289. Min Act: -0.0001
Data Index: 1598233 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.7035. Min Act: -0.0001
Data Index: 299212 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.7213. Min Act: -0.0001
Data Index: 1366735 (Python Code)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.7190. Min Act: -0.0001
Data Index: 1618685 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.6026. Min Act: -0.0001
Data Index: 1513914 (Python Code)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.5722. Min Act: -0.0001
Data Index: 113640 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.6534. Min Act: -0.0001
Data Index: 1448453 (Python Code)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.6364. Min Act: -0.0001
Data Index: 764026 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.6813. Min Act: -0.0001
Data Index: 1422168 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.7303. Min Act: -0.0000
Data Index: 1342971 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.6653. Min Act: -0.0001
Data Index: 1369270 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.6455. Min Act: -0.0001
Data Index: 1461891 (Python Code)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.6008. Min Act: -0.0001
Data Index: 1352135 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.6426. Min Act: -0.0001
Data Index: 47984 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.4865. Min Act: -0.0001
Data Index: 1655568 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.4607. Min Act: -0.0001
Data Index: 424422 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.5296. Min Act: -0.0001
Data Index: 1632330 (Python Code)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.5711. Min Act: -0.0001
Data Index: 962096 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1677. Min Range: -2.1677
Max Act: 1.5121. Min Act: -0.0001
Data Index: 598047 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19