Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2814 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0098. Min Range: -2.0098
Max Act: 2.0098. Min Act: -0.0001
Data Index: 1341225 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8978. Min Act: -0.0001
Data Index: 810381 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8337. Min Act: -0.0001
Data Index: 812231 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.5997. Min Act: -0.0001
Data Index: 1305686 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.5107. Min Act: -0.0001
Data Index: 907401 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.5423. Min Act: -0.0001
Data Index: 252741 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.4722. Min Act: -0.0001
Data Index: 881908 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.5091. Min Act: -0.0001
Data Index: 903190 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.4234. Min Act: -0.0001
Data Index: 1301522 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.3705. Min Act: -0.0001
Data Index: 693859 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.3609. Min Act: -0.0001
Data Index: 1357175 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.4286. Min Act: -0.0001
Data Index: 311164 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.3374. Min Act: -0.0001
Data Index: 329997 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.1972. Min Act: -0.0001
Data Index: 1301898 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.3433. Min Act: -0.0001
Data Index: 593407 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.2510. Min Act: -0.0001
Data Index: 362574 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.2431. Min Act: -0.0001
Data Index: 458725 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.1627. Min Act: -0.0001
Data Index: 530531 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.2008. Min Act: -0.0001
Data Index: 567513 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.1298. Min Act: -0.0001
Data Index: 317869 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19