Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2672 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.3873. Min Act: -0.0001
Data Index: 1238164 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.3430. Min Act: -0.0001
Data Index: 842313 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.3756. Min Act: -0.0001
Data Index: 929822 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.2264. Min Act: -0.0001
Data Index: 446297 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.3239. Min Act: -0.0001
Data Index: 249338 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.0282. Min Act: -0.0001
Data Index: 276844 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9860. Min Act: -0.0001
Data Index: 1090380 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.8919. Min Act: -0.0001
Data Index: 1047728 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.1026. Min Act: -0.0001
Data Index: 717687 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9822. Min Act: -0.0001
Data Index: 657095 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9749. Min Act: -0.0001
Data Index: 539488 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9519. Min Act: -0.0001
Data Index: 454305 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9410. Min Act: -0.0001
Data Index: 1162195 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9243. Min Act: -0.0001
Data Index: 1093815 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9404. Min Act: -0.0001
Data Index: 1313675 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.0270. Min Act: -0.0000
Data Index: 353477 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9241. Min Act: -0.0001
Data Index: 11299 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.0228. Min Act: -0.0001
Data Index: 8252 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3873. Min Range: -2.3873
Max Act: 2.0219. Min Act: -0.0001
Data Index: 1081065 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3873. Min Range: -2.3873
Max Act: 1.9152. Min Act: -0.0001
Data Index: 875239 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19