Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3695 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.6390. Min Act: -0.0001
Data Index: 288199 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.6971. Min Act: -0.0001
Data Index: 486804 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.6332. Min Act: -0.0001
Data Index: 761191 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.6539. Min Act: -0.0001
Data Index: 897294 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5708. Min Act: -0.0001
Data Index: 380398 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5861. Min Act: -0.0000
Data Index: 848264 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.6236. Min Act: -0.0001
Data Index: 1115049 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5708. Min Act: -0.0001
Data Index: 1647802 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5405. Min Act: -0.0001
Data Index: 1141299 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5665. Min Act: -0.0001
Data Index: 36347 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5493. Min Act: -0.0001
Data Index: 503490 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5599. Min Act: -0.0001
Data Index: 1235357 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5314. Min Act: -0.0001
Data Index: 579659 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5306. Min Act: -0.0001
Data Index: 335059 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5128. Min Act: -0.0001
Data Index: 232701 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.4899. Min Act: -0.0001
Data Index: 802772 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5070. Min Act: -0.0001
Data Index: 1124826 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.4721. Min Act: -0.0001
Data Index: 1317361 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5264. Min Act: -0.0001
Data Index: 682180 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6971. Min Range: -0.6971
Max Act: 0.5041. Min Act: -0.0001
Data Index: 421422 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19