Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2224 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.8442. Min Act: -0.0001
Data Index: 1109531 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.7944. Min Act: -0.0001
Data Index: 253149 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.6816. Min Act: -0.0001
Data Index: 334630 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.6988. Min Act: -0.0001
Data Index: 577958 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.5904. Min Act: -0.0001
Data Index: 260012 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.5433. Min Act: -0.0001
Data Index: 36332 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.5755. Min Act: -0.0001
Data Index: 1135431 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.6428. Min Act: -0.0001
Data Index: 322433 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.5478. Min Act: -0.0001
Data Index: 1280769 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.5094. Min Act: -0.0001
Data Index: 144708 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.4264. Min Act: -0.0001
Data Index: 1008499 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.5142. Min Act: -0.0001
Data Index: 547139 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.4630. Min Act: -0.0001
Data Index: 1185682 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.4455. Min Act: -0.0001
Data Index: 35718 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.3826. Min Act: -0.0001
Data Index: 860570 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.3648. Min Act: -0.0001
Data Index: 1124695 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.4171. Min Act: -0.0001
Data Index: 428834 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.3224. Min Act: -0.0001
Data Index: 403798 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.3836. Min Act: -0.0001
Data Index: 1165446 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8442. Min Range: -1.8442
Max Act: 1.4157. Min Act: -0.0001
Data Index: 277538 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19