Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5721 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.4465. Min Act: -0.0002

Data Index: 693595 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.4169. Min Act: -0.0002

Data Index: 14717 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.3333. Min Act: -0.0002

Data Index: 516682 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.3129. Min Act: -0.0002

Data Index: 418902 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.3064. Min Act: -0.0002

Data Index: 90584 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.3063. Min Act: -0.0002

Data Index: 905985 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.3103. Min Act: -0.0002

Data Index: 334535 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2881. Min Act: -0.0002

Data Index: 795330 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2987. Min Act: -0.0002

Data Index: 825608 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2908. Min Act: -0.0002

Data Index: 385099 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.3062. Min Act: -0.0002

Data Index: 143506 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.3005. Min Act: -0.0002

Data Index: 1020576 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2833. Min Act: -0.0002

Data Index: 837726 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2826. Min Act: -0.0002

Data Index: 77436 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2385. Min Act: -0.0002

Data Index: 967673 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2510. Min Act: -0.0002

Data Index: 1071996 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2626. Min Act: -0.0002

Data Index: 1267169 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2495. Min Act: -0.0002

Data Index: 1172935 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2225. Min Act: -0.0002

Data Index: 1124645 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 1.4465. Min Range: -1.4465

Max Act: 1.2126. Min Act: -0.0002

Data Index: 1339645 (C4 (Web Text))

Max Activating Token Index: 824