Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1811 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.7150. Min Act: -0.0001
Data Index: 1022214 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.3641. Min Act: -0.0001
Data Index: 626599 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.4037. Min Act: -0.0001
Data Index: 1359026 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.3200. Min Act: -0.0001
Data Index: 313196 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.2844. Min Act: -0.0001
Data Index: 1352974 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.4198. Min Act: -0.0001
Data Index: 147959 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.2485. Min Act: -0.0001
Data Index: 1205742 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.0410. Min Act: -0.0001
Data Index: 1168947 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.0189. Min Act: -0.0001
Data Index: 757148 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.0910. Min Act: -0.0001
Data Index: 515409 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7150. Min Range: -2.7150
Max Act: 1.9644. Min Act: -0.0001
Data Index: 942833 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.2666. Min Act: -0.0001
Data Index: 76753 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.0412. Min Act: -0.0001
Data Index: 130610 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7150. Min Range: -2.7150
Max Act: 1.9145. Min Act: -0.0001
Data Index: 963884 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.0996. Min Act: -0.0001
Data Index: 1299994 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7150. Min Range: -2.7150
Max Act: 2.0123. Min Act: -0.0001
Data Index: 59159 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7150. Min Range: -2.7150
Max Act: 1.9257. Min Act: -0.0001
Data Index: 176565 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7150. Min Range: -2.7150
Max Act: 1.9908. Min Act: -0.0001
Data Index: 510205 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7150. Min Range: -2.7150
Max Act: 1.8846. Min Act: -0.0001
Data Index: 962116 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7150. Min Range: -2.7150
Max Act: 1.6588. Min Act: -0.0001
Data Index: 265958 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19