Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4374. Min Act: -0.0001

Data Index: 757217 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4205. Min Act: -0.0001

Data Index: 644875 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3643. Min Act: -0.0001

Data Index: 627993 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4009. Min Act: -0.0001

Data Index: 1082567 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3110. Min Act: -0.0001

Data Index: 690261 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3828. Min Act: -0.0001

Data Index: 97461 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3792. Min Act: -0.0001

Data Index: 3076 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3741. Min Act: -0.0001

Data Index: 851124 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3355. Min Act: -0.0001

Data Index: 1255885 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3439. Min Act: -0.0001

Data Index: 79663 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3100. Min Act: -0.0001

Data Index: 740910 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3246. Min Act: -0.0001

Data Index: 243541 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3313. Min Act: -0.0001

Data Index: 6854 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3131. Min Act: -0.0001

Data Index: 788905 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3337. Min Act: -0.0001

Data Index: 343363 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3069. Min Act: -0.0001

Data Index: 22068 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3241. Min Act: -0.0001

Data Index: 1196827 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3166. Min Act: -0.0001

Data Index: 329747 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1339578 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.2925. Min Act: -0.0001

Data Index: 1180970 (C4 (Web Text))

Max Activating Token Index: 964