Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3119 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3763. Min Range: -1.3763
Max Act: 1.2595. Min Act: -0.0001
Data Index: 1273162 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3763. Min Range: -1.3763
Max Act: 1.3763. Min Act: -0.0001
Data Index: 214694 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3763. Min Range: -1.3763
Max Act: 1.1567. Min Act: -0.0001
Data Index: 637331 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3763. Min Range: -1.3763
Max Act: 1.0151. Min Act: -0.0001
Data Index: 545237 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3763. Min Range: -1.3763
Max Act: 1.1168. Min Act: -0.0001
Data Index: 1053781 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3763. Min Range: -1.3763
Max Act: 1.0389. Min Act: -0.0001
Data Index: 966262 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9447. Min Act: -0.0001
Data Index: 790411 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9822. Min Act: -0.0001
Data Index: 266517 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3763. Min Range: -1.3763
Max Act: 1.0050. Min Act: -0.0001
Data Index: 55711 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9880. Min Act: -0.0001
Data Index: 1640066 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9011. Min Act: -0.0001
Data Index: 991124 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9462. Min Act: -0.0001
Data Index: 79265 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9709. Min Act: -0.0001
Data Index: 1316107 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9121. Min Act: -0.0001
Data Index: 1160102 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9379. Min Act: -0.0001
Data Index: 527969 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9658. Min Act: -0.0001
Data Index: 661752 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9594. Min Act: -0.0001
Data Index: 1061778 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.8550. Min Act: -0.0001
Data Index: 1653913 (Python Code)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.9637. Min Act: -0.0001
Data Index: 217097 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3763. Min Range: -1.3763
Max Act: 0.7801. Min Act: -0.0001
Data Index: 933568 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19