Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3711 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.8884. Min Act: -0.0001
Data Index: 616684 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.9679. Min Act: -0.0001
Data Index: 688544 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3547. Min Range: -3.3547
Max Act: 3.3547. Min Act: -0.0001
Data Index: 1355575 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.8296. Min Act: -0.0001
Data Index: 181793 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.6445. Min Act: -0.0001
Data Index: 882973 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.6001. Min Act: -0.0001
Data Index: 227287 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.5142. Min Act: -0.0001
Data Index: 1316 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.4934. Min Act: -0.0001
Data Index: 1280337 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.4738. Min Act: -0.0001
Data Index: 439052 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.4585. Min Act: -0.0001
Data Index: 462874 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.1313. Min Act: -0.0001
Data Index: 159833 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.3696. Min Act: -0.0001
Data Index: 487867 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.4621. Min Act: -0.0001
Data Index: 1303779 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.2157. Min Act: -0.0001
Data Index: 1121946 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.0913. Min Act: -0.0001
Data Index: 693951 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.2748. Min Act: -0.0001
Data Index: 242842 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.1492. Min Act: -0.0001
Data Index: 638580 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.1509. Min Act: -0.0001
Data Index: 1272163 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.3188. Min Act: -0.0001
Data Index: 279103 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3547. Min Range: -3.3547
Max Act: 2.1947. Min Act: -0.0001
Data Index: 299968 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19