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

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

Neuron 84 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.6001. Min Act: -0.0001

Data Index: 281821 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.7140. Min Act: -0.0001

Data Index: 164803 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4333. Min Act: -0.0001

Data Index: 228190 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3849. Min Act: -0.0001

Data Index: 965089 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3598. Min Act: -0.0001

Data Index: 767691 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3970. Min Act: -0.0001

Data Index: 381902 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4144. Min Act: -0.0001

Data Index: 1013324 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3250. Min Act: -0.0001

Data Index: 610108 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3936. Min Act: -0.0001

Data Index: 293708 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3347. Min Act: -0.0001

Data Index: 436683 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1749. Min Act: -0.0001

Data Index: 602751 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2861. Min Act: -0.0001

Data Index: 217699 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2418. Min Act: -0.0001

Data Index: 672617 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1739. Min Act: -0.0001

Data Index: 629317 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3004. Min Act: -0.0001

Data Index: 1304708 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3646. Min Act: -0.0001

Data Index: 42069 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2954. Min Act: -0.0001

Data Index: 482679 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1743. Min Act: -0.0001

Data Index: 684014 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2363. Min Act: -0.0001

Data Index: 675142 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1972. Min Act: -0.0001

Data Index: 1115644 (C4 (Web Text))

Max Activating Token Index: 734