Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 147 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2620. Min Range: -2.2620

Max Act: 2.2385. Min Act: -0.0001

Data Index: 137465 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 2.2620. Min Range: -2.2620

Max Act: 2.2620. Min Act: -0.0001

Data Index: 726922 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 2.2620. Min Range: -2.2620

Max Act: 2.0301. Min Act: -0.0001

Data Index: 184067 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.7469. Min Act: -0.0000

Data Index: 782027 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.9076. Min Act: -0.0001

Data Index: 1218963 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.9164. Min Act: -0.0000

Data Index: 144352 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.6165. Min Act: -0.0000

Data Index: 942298 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.6637. Min Act: -0.0001

Data Index: 228540 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.5365. Min Act: -0.0000

Data Index: 918199 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.5991. Min Act: -0.0001

Data Index: 332387 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.5646. Min Act: -0.0001

Data Index: 834733 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.7021. Min Act: -0.0001

Data Index: 1163854 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.5045. Min Act: -0.0000

Data Index: 886118 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.5577. Min Act: -0.0000

Data Index: 835481 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.3345. Min Act: -0.0000

Data Index: 766017 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.6483. Min Act: -0.0001

Data Index: 1146980 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.5922. Min Act: -0.0000

Data Index: 413492 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.5327. Min Act: -0.0000

Data Index: 1344819 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.4387. Min Act: -0.0001

Data Index: 608707 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 2.2620. Min Range: -2.2620

Max Act: 1.4947. Min Act: -0.0000

Data Index: 637450 (C4 (Web Text))

Max Activating Token Index: 816