Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2798 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.3465. Min Act: -0.0001
Data Index: 50555 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.6601. Min Act: -0.0001
Data Index: 1346329 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.1007. Min Act: -0.0001
Data Index: 985742 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.2545. Min Act: -0.0001
Data Index: 1207750 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.2073. Min Act: -0.0001
Data Index: 982079 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.1907. Min Act: -0.0001
Data Index: 761443 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.5132. Min Act: -0.0001
Data Index: 1032932 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6601. Min Range: -2.6601
Max Act: 1.9654. Min Act: -0.0001
Data Index: 202507 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6601. Min Range: -2.6601
Max Act: 1.9729. Min Act: -0.0001
Data Index: 1224335 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.1579. Min Act: -0.0001
Data Index: 896162 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.3501. Min Act: -0.0001
Data Index: 1044346 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6601. Min Range: -2.6601
Max Act: 1.8338. Min Act: -0.0001
Data Index: 105261 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.1487. Min Act: -0.0001
Data Index: 39782 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.2277. Min Act: -0.0001
Data Index: 935841 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6601. Min Range: -2.6601
Max Act: 1.9758. Min Act: -0.0001
Data Index: 32568 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6601. Min Range: -2.6601
Max Act: 1.9981. Min Act: -0.0001
Data Index: 510604 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.0161. Min Act: -0.0001
Data Index: 355565 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.0545. Min Act: -0.0001
Data Index: 1240892 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.0547. Min Act: -0.0001
Data Index: 1342367 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6601. Min Range: -2.6601
Max Act: 2.2288. Min Act: -0.0001
Data Index: 1211689 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19