Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2650 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.5024. Min Range: -2.5024
Max Act: 2.5024. Min Act: -0.0002
Data Index: 588778 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.9832. Min Act: -0.0001
Data Index: 1145259 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.8166. Min Act: -0.0002
Data Index: 553825 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5024. Min Range: -2.5024
Max Act: 2.2835. Min Act: -0.0002
Data Index: 1092411 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.9497. Min Act: -0.0002
Data Index: 755442 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5024. Min Range: -2.5024
Max Act: 2.0233. Min Act: -0.0002
Data Index: 409948 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.7861. Min Act: -0.0002
Data Index: 575446 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.6708. Min Act: -0.0002
Data Index: 1092306 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.8951. Min Act: -0.0002
Data Index: 749516 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.7568. Min Act: -0.0002
Data Index: 741424 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.8787. Min Act: -0.0002
Data Index: 959690 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.8271. Min Act: -0.0002
Data Index: 697627 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.5687. Min Act: -0.0001
Data Index: 1155845 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.3990. Min Act: -0.0002
Data Index: 625808 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.7428. Min Act: -0.0001
Data Index: 562033 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.6411. Min Act: -0.0002
Data Index: 267893 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.5582. Min Act: -0.0002
Data Index: 817493 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.6416. Min Act: -0.0001
Data Index: 809747 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.5951. Min Act: -0.0002
Data Index: 64560 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5024. Min Range: -2.5024
Max Act: 1.5476. Min Act: -0.0001
Data Index: 548844 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19