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

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

Neuron 1895 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0142. Min Act: -0.0003

Data Index: 63896 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1137680 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1094139 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0138. Min Act: -0.0003

Data Index: 375093 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0140. Min Act: -0.0003

Data Index: 341352 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0129. Min Act: -0.0003

Data Index: 867277 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0126. Min Act: -0.0003

Data Index: 284362 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0129. Min Act: -0.0003

Data Index: 141136 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0117. Min Act: -0.0003

Data Index: 677188 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0114. Min Act: -0.0003

Data Index: 770265 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0129. Min Act: -0.0003

Data Index: 624707 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1653057 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1202405 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0123. Min Act: -0.0003

Data Index: 559491 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0120. Min Act: -0.0003

Data Index: 38591 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1585934 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0118. Min Act: -0.0003

Data Index: 47169 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1159608 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0113. Min Act: -0.0003

Data Index: 956383 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.0163. Min Range: -0.0163

Max Act: 0.0117. Min Act: -0.0003

Data Index: 163247 (C4 (Web Text))

Max Activating Token Index: 802