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

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

Neuron 3682 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: 0.4195. Min Range: -0.4195

Max Act: 0.4195. Min Act: -0.0001

Data Index: 860218 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.4054. Min Act: -0.0001

Data Index: 790999 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3905. Min Act: -0.0001

Data Index: 524541 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3879. Min Act: -0.0001

Data Index: 1199020 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3890. Min Act: -0.0001

Data Index: 806159 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3764. Min Act: -0.0001

Data Index: 126399 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3435. Min Act: -0.0001

Data Index: 1303791 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3411. Min Act: -0.0001

Data Index: 1326999 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3352. Min Act: -0.0001

Data Index: 743958 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3332. Min Act: -0.0001

Data Index: 515893 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3293. Min Act: -0.0001

Data Index: 772700 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3159. Min Act: -0.0001

Data Index: 785083 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3148. Min Act: -0.0001

Data Index: 939009 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3356. Min Act: -0.0001

Data Index: 574399 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3090. Min Act: -0.0001

Data Index: 337976 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3079. Min Act: -0.0001

Data Index: 341037 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3250. Min Act: -0.0001

Data Index: 696508 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3139. Min Act: -0.0001

Data Index: 663037 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3136. Min Act: -0.0001

Data Index: 514421 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3116. Min Act: -0.0001

Data Index: 1128053 (C4 (Web Text))

Max Activating Token Index: 236