Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 999 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.2741. Min Range: -4.2741
Max Act: 4.2560. Min Act: -0.0001
Data Index: 1246125 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2741. Min Range: -4.2741
Max Act: 4.2741. Min Act: -0.0001
Data Index: 732419 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2741. Min Range: -4.2741
Max Act: 4.0118. Min Act: -0.0001
Data Index: 623769 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.7303. Min Act: -0.0001
Data Index: 717295 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.3529. Min Act: -0.0001
Data Index: 301746 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.5105. Min Act: -0.0001
Data Index: 1356195 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.4436. Min Act: -0.0001
Data Index: 437029 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.3571. Min Act: -0.0001
Data Index: 414579 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.3260. Min Act: -0.0001
Data Index: 1269420 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.3283. Min Act: -0.0001
Data Index: 657800 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.2911. Min Act: -0.0001
Data Index: 15905 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.2643. Min Act: -0.0001
Data Index: 689692 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.2934. Min Act: -0.0001
Data Index: 337402 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.4932. Min Act: -0.0001
Data Index: 279485 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.2163. Min Act: -0.0001
Data Index: 844977 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.3033. Min Act: -0.0001
Data Index: 208359 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.0371. Min Act: -0.0001
Data Index: 1089729 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.0556. Min Act: -0.0001
Data Index: 441633 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2741. Min Range: -4.2741
Max Act: 2.9293. Min Act: -0.0001
Data Index: 390558 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2741. Min Range: -4.2741
Max Act: 3.4907. Min Act: -0.0001
Data Index: 549891 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19