Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1971 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.6435. Min Act: -0.0001
Data Index: 1395811 (Python Code)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.6241. Min Act: -0.0001
Data Index: 1524445 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.6336. Min Act: -0.0001
Data Index: 1465841 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.6015. Min Act: -0.0001
Data Index: 1377732 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.6435. Min Act: -0.0001
Data Index: 1600240 (Python Code)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5926. Min Act: -0.0001
Data Index: 1620186 (Python Code)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5669. Min Act: -0.0001
Data Index: 1518158 (Python Code)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5507. Min Act: -0.0001
Data Index: 1431406 (Python Code)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5501. Min Act: -0.0001
Data Index: 1579566 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5672. Min Act: -0.0001
Data Index: 1559989 (Python Code)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5747. Min Act: -0.0001
Data Index: 1541335 (Python Code)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5673. Min Act: -0.0001
Data Index: 1392424 (Python Code)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5389. Min Act: -0.0001
Data Index: 1509101 (Python Code)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5053. Min Act: -0.0001
Data Index: 1596767 (Python Code)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5180. Min Act: -0.0001
Data Index: 1618597 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5002. Min Act: -0.0001
Data Index: 1408072 (Python Code)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.5661. Min Act: -0.0001
Data Index: 1528156 (Python Code)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.4914. Min Act: -0.0001
Data Index: 1487276 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.4476. Min Act: -0.0001
Data Index: 1560957 (Python Code)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6435. Min Range: -0.6435
Max Act: 0.4941. Min Act: -0.0001
Data Index: 1589438 (Python Code)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19