Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1913 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.6951. Min Act: -0.0001
Data Index: 594433 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.7569. Min Act: -0.0001
Data Index: 1018025 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.5459. Min Act: -0.0001
Data Index: 523224 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.4834. Min Act: -0.0001
Data Index: 380256 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.3100. Min Act: -0.0001
Data Index: 383300 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.2620. Min Act: -0.0001
Data Index: 222726 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.2457. Min Act: -0.0001
Data Index: 188370 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.1118. Min Act: -0.0001
Data Index: 236945 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.1623. Min Act: -0.0001
Data Index: 643571 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.1418. Min Act: -0.0001
Data Index: 1073479 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.1348. Min Act: -0.0001
Data Index: 840184 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7569. Min Range: -2.7569
Max Act: 1.9655. Min Act: -0.0001
Data Index: 201058 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.0643. Min Act: -0.0001
Data Index: 35772 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.0409. Min Act: -0.0001
Data Index: 1091720 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7569. Min Range: -2.7569
Max Act: 1.8361. Min Act: -0.0001
Data Index: 826148 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.0176. Min Act: -0.0001
Data Index: 469782 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.1244. Min Act: -0.0001
Data Index: 1277270 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.1179. Min Act: -0.0001
Data Index: 1346499 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.1964. Min Act: -0.0001
Data Index: 51557 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7569. Min Range: -2.7569
Max Act: 2.0698. Min Act: -0.0001
Data Index: 1241749 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19