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

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

Neuron 695 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3905. Min Act: -0.0001

Data Index: 439070 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3622. Min Act: -0.0001

Data Index: 259983 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3390. Min Act: -0.0001

Data Index: 211807 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3455. Min Act: -0.0000

Data Index: 422135 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3240. Min Act: -0.0000

Data Index: 928701 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3314. Min Act: -0.0000

Data Index: 557515 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1302145 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3110. Min Act: -0.0001

Data Index: 101465 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1057384 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3210. Min Act: -0.0001

Data Index: 442294 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3146. Min Act: -0.0000

Data Index: 306005 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1190147 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1052201 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2954. Min Act: -0.0000

Data Index: 566138 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1249877 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3084. Min Act: -0.0001

Data Index: 996356 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2852. Min Act: -0.0001

Data Index: 73732 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2924. Min Act: -0.0000

Data Index: 105561 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1164051 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.3905. Min Range: -0.3905

Max Act: 0.2913. Min Act: -0.0000

Data Index: 262812 (C4 (Web Text))

Max Activating Token Index: 746