Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3479 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.8788. Min Act: -0.0001
Data Index: 591083 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.8465. Min Act: -0.0001
Data Index: 620610 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.9536. Min Act: -0.0001
Data Index: 117797 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.8109. Min Act: -0.0001
Data Index: 279647 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.8308. Min Act: -0.0001
Data Index: 1314605 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0953. Min Range: -2.0953
Max Act: 2.0953. Min Act: -0.0001
Data Index: 666563 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.9583. Min Act: -0.0001
Data Index: 699104 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.8199. Min Act: -0.0001
Data Index: 170330 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.8060. Min Act: -0.0001
Data Index: 218276 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.6280. Min Act: -0.0001
Data Index: 1298814 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.7208. Min Act: -0.0001
Data Index: 677330 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.7886. Min Act: -0.0001
Data Index: 1333609 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.7993. Min Act: -0.0001
Data Index: 629096 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.7525. Min Act: -0.0001
Data Index: 711641 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.4092. Min Act: -0.0001
Data Index: 426008 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.5617. Min Act: -0.0001
Data Index: 1265645 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.6326. Min Act: -0.0001
Data Index: 1142651 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.7041. Min Act: -0.0001
Data Index: 1066960 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.6019. Min Act: -0.0001
Data Index: 1113538 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0953. Min Range: -2.0953
Max Act: 1.3387. Min Act: -0.0001
Data Index: 786333 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19