Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2180 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.3105. Min Act: -0.0001

Data Index: 463534 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.3019. Min Act: -0.0001

Data Index: 484036 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2728. Min Act: -0.0001

Data Index: 809410 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2643. Min Act: -0.0001

Data Index: 177161 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2511. Min Act: -0.0001

Data Index: 808238 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2540. Min Act: -0.0001

Data Index: 358698 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2559. Min Act: -0.0001

Data Index: 963666 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2419. Min Act: -0.0001

Data Index: 478136 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2367. Min Act: -0.0001

Data Index: 140172 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2357. Min Act: -0.0001

Data Index: 556721 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2589. Min Act: -0.0001

Data Index: 1340474 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2262. Min Act: -0.0001

Data Index: 788408 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2062. Min Act: -0.0001

Data Index: 680444 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2284. Min Act: -0.0001

Data Index: 1101707 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2134. Min Act: -0.0001

Data Index: 763155 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2143. Min Act: -0.0001

Data Index: 2511 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2284. Min Act: -0.0001

Data Index: 408042 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1248517 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2498. Min Act: -0.0001

Data Index: 433874 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.3105. Min Range: -0.3105

Max Act: 0.2188. Min Act: -0.0001

Data Index: 550094 (C4 (Web Text))

Max Activating Token Index: 761