Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3000 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2789. Min Act: -0.0001
Data Index: 718612 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2973. Min Act: -0.0001
Data Index: 144975 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2816. Min Act: -0.0001
Data Index: 1237699 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2765. Min Act: -0.0001
Data Index: 784277 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2572. Min Act: -0.0001
Data Index: 373789 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2711. Min Act: -0.0001
Data Index: 396964 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2703. Min Act: -0.0001
Data Index: 1211928 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2599. Min Act: -0.0001
Data Index: 1353298 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2551. Min Act: -0.0001
Data Index: 389380 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2729. Min Act: -0.0001
Data Index: 652596 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2706. Min Act: -0.0001
Data Index: 127718 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2605. Min Act: -0.0001
Data Index: 587888 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2586. Min Act: -0.0001
Data Index: 721716 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2476. Min Act: -0.0001
Data Index: 980379 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2546. Min Act: -0.0001
Data Index: 684701 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2440. Min Act: -0.0001
Data Index: 49625 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2622. Min Act: -0.0001
Data Index: 197527 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2507. Min Act: -0.0001
Data Index: 212338 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2587. Min Act: -0.0001
Data Index: 16645 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2973. Min Range: -0.2973
Max Act: 0.2570. Min Act: -0.0001
Data Index: 228935 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19