Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2248 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.1379. Min Act: -0.0001
Data Index: 1587398 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.1235. Min Act: -0.0001
Data Index: 1412723 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.2300. Min Act: -0.0001
Data Index: 1629059 (Python Code)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.2067. Min Act: -0.0001
Data Index: 1427420 (Python Code)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.1758. Min Act: -0.0001
Data Index: 1588684 (Python Code)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.0138. Min Act: -0.0001
Data Index: 1484190 (Python Code)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.1294. Min Act: -0.0001
Data Index: 1593992 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.0923. Min Act: -0.0001
Data Index: 1400317 (Python Code)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.0404. Min Act: -0.0001
Data Index: 1644755 (Python Code)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.1152. Min Act: -0.0001
Data Index: 1512349 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.0151. Min Act: -0.0001
Data Index: 1620886 (Python Code)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.0065. Min Act: -0.0001
Data Index: 1513193 (Python Code)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2300. Min Range: -2.2300
Max Act: 1.9758. Min Act: -0.0001
Data Index: 1564209 (Python Code)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2300. Min Range: -2.2300
Max Act: 1.9526. Min Act: -0.0001
Data Index: 1473366 (Python Code)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2300. Min Range: -2.2300
Max Act: 1.9433. Min Act: -0.0001
Data Index: 1359880 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.0303. Min Act: -0.0001
Data Index: 1513601 (Python Code)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.0188. Min Act: -0.0001
Data Index: 1430409 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2300. Min Range: -2.2300
Max Act: 2.0104. Min Act: -0.0001
Data Index: 1424670 (Python Code)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2300. Min Range: -2.2300
Max Act: 1.8192. Min Act: -0.0001
Data Index: 1595209 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2300. Min Range: -2.2300
Max Act: 1.8854. Min Act: -0.0001
Data Index: 1614972 (Python Code)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19