Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3249 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.9172. Min Act: -0.0001
Data Index: 1394318 (Python Code)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.7749. Min Act: -0.0001
Data Index: 1408018 (Python Code)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.7718. Min Act: -0.0001
Data Index: 661888 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.7605. Min Act: -0.0001
Data Index: 276495 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.7340. Min Act: -0.0001
Data Index: 1619089 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.8479. Min Act: -0.0001
Data Index: 1425128 (Python Code)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6923. Min Act: -0.0001
Data Index: 440024 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.7011. Min Act: -0.0001
Data Index: 1608198 (Python Code)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.7190. Min Act: -0.0001
Data Index: 1513299 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6939. Min Act: -0.0001
Data Index: 90749 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.7096. Min Act: -0.0001
Data Index: 525070 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.7405. Min Act: -0.0001
Data Index: 62126 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6015. Min Act: -0.0001
Data Index: 67223 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6837. Min Act: -0.0001
Data Index: 1117473 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6347. Min Act: -0.0001
Data Index: 1404335 (Python Code)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6660. Min Act: -0.0001
Data Index: 1467430 (Python Code)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6388. Min Act: -0.0001
Data Index: 1426069 (Python Code)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6818. Min Act: -0.0001
Data Index: 1605028 (Python Code)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6606. Min Act: -0.0001
Data Index: 1558826 (Python Code)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9172. Min Range: -0.9172
Max Act: 0.6615. Min Act: -0.0001
Data Index: 850184 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19