Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2052 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.3935. Min Act: -0.0001
Data Index: 339852 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.3429. Min Act: -0.0001
Data Index: 857551 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.3266. Min Act: -0.0001
Data Index: 153463 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.3128. Min Act: -0.0001
Data Index: 410110 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.3071. Min Act: -0.0001
Data Index: 387995 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.3229. Min Act: -0.0001
Data Index: 1320512 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.3081. Min Act: -0.0001
Data Index: 325435 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2962. Min Act: -0.0001
Data Index: 45933 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2905. Min Act: -0.0001
Data Index: 881925 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2742. Min Act: -0.0001
Data Index: 385111 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2815. Min Act: -0.0001
Data Index: 91463 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2906. Min Act: -0.0001
Data Index: 300169 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2780. Min Act: -0.0001
Data Index: 420148 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2756. Min Act: -0.0001
Data Index: 1356556 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2664. Min Act: -0.0000
Data Index: 144316 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2757. Min Act: -0.0001
Data Index: 424378 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2741. Min Act: -0.0001
Data Index: 868367 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2662. Min Act: -0.0001
Data Index: 1307500 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2692. Min Act: -0.0000
Data Index: 892111 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3935. Min Range: -0.3935
Max Act: 0.2698. Min Act: -0.0001
Data Index: 312020 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19