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

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

Neuron 3151 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: 0.5330. Min Range: -0.5330

Max Act: 0.5330. Min Act: -0.0001

Data Index: 80123 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4949. Min Act: 0.0001

Data Index: 625145 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4978. Min Act: 0.0000

Data Index: 218172 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4591. Min Act: -0.0000

Data Index: 915819 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4384. Min Act: -0.0001

Data Index: 833311 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4495. Min Act: -0.0000

Data Index: 571210 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4373. Min Act: -0.0000

Data Index: 172476 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4322. Min Act: -0.0001

Data Index: 550680 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4334. Min Act: -0.0001

Data Index: 48505 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4050. Min Act: -0.0000

Data Index: 137867 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4119. Min Act: -0.0001

Data Index: 1039119 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.3952. Min Act: -0.0000

Data Index: 254606 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.3914. Min Act: 0.0000

Data Index: 614995 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.4053. Min Act: -0.0000

Data Index: 491186 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.3729. Min Act: -0.0001

Data Index: 896807 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.3853. Min Act: -0.0000

Data Index: 633038 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.3850. Min Act: -0.0001

Data Index: 757655 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1028368 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.3851. Min Act: -0.0000

Data Index: 694529 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.5330. Min Range: -0.5330

Max Act: 0.3717. Min Act: 0.0000

Data Index: 143496 (C4 (Web Text))

Max Activating Token Index: 723