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

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

Neuron 2516 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: 3.2931. Min Range: -3.2931

Max Act: 3.2931. Min Act: -0.0001

Data Index: 292944 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.7596. Min Act: -0.0001

Data Index: 727687 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.8552. Min Act: -0.0001

Data Index: 652320 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.6641. Min Act: -0.0001

Data Index: 956263 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.7743. Min Act: -0.0001

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.7318. Min Act: -0.0001

Data Index: 1096495 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.7179. Min Act: -0.0001

Data Index: 354195 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.8543. Min Act: -0.0001

Data Index: 191167 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.6942. Min Act: -0.0001

Data Index: 85596 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.8461. Min Act: -0.0001

Data Index: 26435 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.6416. Min Act: -0.0001

Data Index: 266803 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.5856. Min Act: -0.0001

Data Index: 98277 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.5853. Min Act: -0.0001

Data Index: 777595 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.6826. Min Act: -0.0001

Data Index: 1144584 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.4074. Min Act: -0.0001

Data Index: 208071 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.3811. Min Act: -0.0001

Data Index: 701197 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.4982. Min Act: -0.0001

Data Index: 65102 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.3310. Min Act: -0.0001

Data Index: 872107 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.4587. Min Act: -0.0001

Data Index: 117046 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 3.2931. Min Range: -3.2931

Max Act: 2.4651. Min Act: -0.0001

Data Index: 690956 (C4 (Web Text))

Max Activating Token Index: 529