Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2644 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.4114. Min Act: -0.0001

Data Index: 207078 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2685. Min Act: -0.0001

Data Index: 1166284 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2988. Min Act: -0.0001

Data Index: 1128993 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3092. Min Act: -0.0002

Data Index: 845607 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3079. Min Act: -0.0002

Data Index: 1163643 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2975. Min Act: -0.0002

Data Index: 294975 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2871. Min Act: -0.0002

Data Index: 501986 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3082. Min Act: -0.0001

Data Index: 222787 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3162. Min Act: -0.0001

Data Index: 676997 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1123283 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3019. Min Act: -0.0002

Data Index: 1319771 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3101. Min Act: -0.0002

Data Index: 495837 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2896. Min Act: -0.0002

Data Index: 859314 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2989. Min Act: -0.0002

Data Index: 932539 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3096. Min Act: -0.0001

Data Index: 1011813 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2862. Min Act: -0.0001

Data Index: 274703 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1000007 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3088. Min Act: -0.0002

Data Index: 269516 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1208671 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.2912. Min Act: -0.0001

Data Index: 780846 (C4 (Web Text))

Max Activating Token Index: 29