Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 242 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1446437 (Python Code)

Max Activating Token Index: 430

Text #1

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1561209 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1461137 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1529146 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1621324 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1560229 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1604960 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1608072 (Python Code)

Max Activating Token Index: 1008

Text #8

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1610056 (Python Code)

Max Activating Token Index: 489

Text #9

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1386672 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1388116 (Python Code)

Max Activating Token Index: 906

Text #11

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1484401 (Python Code)

Max Activating Token Index: 182

Text #12

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1646872 (Python Code)

Max Activating Token Index: 683

Text #13

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1468416 (Python Code)

Max Activating Token Index: 470

Text #14

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1444601 (Python Code)

Max Activating Token Index: 423

Text #15

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1579352 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1404238 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1548371 (Python Code)

Max Activating Token Index: 527

Text #18

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1362508 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 0.0226. Min Range: -0.0226

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1546882 (Python Code)

Max Activating Token Index: 167