Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1819 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.7371. Min Range: -4.7371
Max Act: 4.7371. Min Act: -0.0001
Data Index: 1634436 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7371. Min Range: -4.7371
Max Act: 4.7056. Min Act: -0.0001
Data Index: 1572873 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7371. Min Range: -4.7371
Max Act: 4.1063. Min Act: -0.0001
Data Index: 1364191 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7371. Min Range: -4.7371
Max Act: 4.1850. Min Act: -0.0001
Data Index: 1539045 (Python Code)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7371. Min Range: -4.7371
Max Act: 4.3529. Min Act: -0.0001
Data Index: 1470129 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7371. Min Range: -4.7371
Max Act: 4.3105. Min Act: -0.0001
Data Index: 1487972 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.9230. Min Act: -0.0001
Data Index: 1472731 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7371. Min Range: -4.7371
Max Act: 4.0291. Min Act: -0.0001
Data Index: 1601405 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.9981. Min Act: -0.0001
Data Index: 1400768 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.7440. Min Act: -0.0001
Data Index: 1613676 (Python Code)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.8617. Min Act: -0.0001
Data Index: 1556118 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.6321. Min Act: -0.0001
Data Index: 1383575 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.7291. Min Act: -0.0001
Data Index: 1438637 (Python Code)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.5359. Min Act: -0.0001
Data Index: 1461095 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.8666. Min Act: -0.0001
Data Index: 1522508 (Python Code)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.8512. Min Act: -0.0001
Data Index: 1586122 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.8531. Min Act: -0.0001
Data Index: 1652805 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.3673. Min Act: -0.0001
Data Index: 1374292 (Python Code)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.6264. Min Act: -0.0001
Data Index: 1606064 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7371. Min Range: -4.7371
Max Act: 3.4355. Min Act: -0.0001
Data Index: 1365867 (Python Code)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19