Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1982 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.0469. Min Range: -1.0469
Max Act: 1.0469. Min Act: -0.0001
Data Index: 1612020 (Python Code)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.7115. Min Act: -0.0001
Data Index: 775783 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.6700. Min Act: -0.0001
Data Index: 747201 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.6671. Min Act: -0.0001
Data Index: 1008326 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.6162. Min Act: -0.0001
Data Index: 381056 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.6208. Min Act: -0.0001
Data Index: 1298296 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.6184. Min Act: -0.0001
Data Index: 1522432 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.6106. Min Act: -0.0001
Data Index: 1402677 (Python Code)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.6268. Min Act: -0.0001
Data Index: 1508724 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5710. Min Act: -0.0001
Data Index: 1068091 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5808. Min Act: -0.0001
Data Index: 769504 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5402. Min Act: -0.0001
Data Index: 841660 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5354. Min Act: -0.0001
Data Index: 779569 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5681. Min Act: -0.0001
Data Index: 1602925 (Python Code)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5268. Min Act: -0.0001
Data Index: 1541914 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5273. Min Act: -0.0001
Data Index: 536349 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5811. Min Act: -0.0001
Data Index: 1479532 (Python Code)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5463. Min Act: -0.0001
Data Index: 250915 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.6074. Min Act: -0.0001
Data Index: 1578581 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0469. Min Range: -1.0469
Max Act: 0.5560. Min Act: -0.0001
Data Index: 284734 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19