Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2687 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.0520. Min Range: -1.0520
Max Act: 1.0520. Min Act: -0.0001
Data Index: 1496077 (Python Code)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.9350. Min Act: -0.0001
Data Index: 1200232 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.9796. Min Act: -0.0001
Data Index: 533228 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8768. Min Act: -0.0001
Data Index: 666062 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8692. Min Act: -0.0001
Data Index: 691269 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8669. Min Act: -0.0001
Data Index: 1039100 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.9178. Min Act: -0.0001
Data Index: 787885 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8168. Min Act: -0.0001
Data Index: 591828 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8521. Min Act: -0.0001
Data Index: 818354 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8261. Min Act: -0.0001
Data Index: 1309270 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8494. Min Act: -0.0001
Data Index: 1023708 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.7886. Min Act: -0.0001
Data Index: 91031 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.7929. Min Act: -0.0001
Data Index: 940375 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.7846. Min Act: -0.0001
Data Index: 984444 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8319. Min Act: -0.0001
Data Index: 422922 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8008. Min Act: -0.0001
Data Index: 1427274 (Python Code)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8596. Min Act: -0.0001
Data Index: 938416 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8121. Min Act: -0.0001
Data Index: 115828 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8303. Min Act: -0.0001
Data Index: 833648 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0520. Min Range: -1.0520
Max Act: 0.8584. Min Act: -0.0001
Data Index: 619572 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19