Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3294 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.6010. Min Act: -0.0001
Data Index: 486733 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.2370. Min Act: -0.0001
Data Index: 174444 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.3150. Min Act: -0.0001
Data Index: 592178 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.4980. Min Act: -0.0001
Data Index: 480073 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6010. Min Range: -2.6010
Max Act: 1.8890. Min Act: -0.0000
Data Index: 1326232 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.3539. Min Act: -0.0001
Data Index: 267108 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.2527. Min Act: -0.0001
Data Index: 149335 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6010. Min Range: -2.6010
Max Act: 1.7182. Min Act: -0.0001
Data Index: 751878 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.0713. Min Act: -0.0001
Data Index: 1098675 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6010. Min Range: -2.6010
Max Act: 1.9259. Min Act: -0.0001
Data Index: 994277 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.0037. Min Act: -0.0001
Data Index: 872321 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.0338. Min Act: -0.0001
Data Index: 355945 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6010. Min Range: -2.6010
Max Act: 1.9942. Min Act: -0.0001
Data Index: 380237 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6010. Min Range: -2.6010
Max Act: 1.9601. Min Act: -0.0001
Data Index: 141197 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6010. Min Range: -2.6010
Max Act: 1.5606. Min Act: -0.0001
Data Index: 987327 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.1329. Min Act: -0.0001
Data Index: 821639 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.1153. Min Act: -0.0001
Data Index: 637544 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6010. Min Range: -2.6010
Max Act: 2.0200. Min Act: -0.0001
Data Index: 1078672 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6010. Min Range: -2.6010
Max Act: 1.9135. Min Act: -0.0001
Data Index: 649096 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6010. Min Range: -2.6010
Max Act: 1.8342. Min Act: -0.0001
Data Index: 955170 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19