Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2822 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.1684. Min Range: -4.1684
Max Act: 4.1684. Min Act: -0.0001
Data Index: 7055 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.6505. Min Act: -0.0001
Data Index: 1303208 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.6195. Min Act: -0.0001
Data Index: 491126 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.3632. Min Act: -0.0001
Data Index: 543416 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.6009. Min Act: -0.0001
Data Index: 892916 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.2891. Min Act: -0.0001
Data Index: 773733 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.4071. Min Act: -0.0001
Data Index: 189207 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.3517. Min Act: -0.0001
Data Index: 1207010 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.3576. Min Act: -0.0001
Data Index: 828229 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1684. Min Range: -4.1684
Max Act: 2.9480. Min Act: -0.0001
Data Index: 542734 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.1317. Min Act: -0.0001
Data Index: 1316158 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.1128. Min Act: -0.0001
Data Index: 162267 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.0631. Min Act: -0.0001
Data Index: 1042555 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1684. Min Range: -4.1684
Max Act: 2.7858. Min Act: -0.0001
Data Index: 215621 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.0391. Min Act: -0.0001
Data Index: 125953 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.1638. Min Act: -0.0001
Data Index: 1196937 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.3148. Min Act: -0.0001
Data Index: 1279999 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1684. Min Range: -4.1684
Max Act: 3.0437. Min Act: -0.0001
Data Index: 20373 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1684. Min Range: -4.1684
Max Act: 2.8652. Min Act: -0.0001
Data Index: 389317 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1684. Min Range: -4.1684
Max Act: 2.9844. Min Act: -0.0001
Data Index: 737571 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19