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

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

Neuron 774 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: 0.7105. Min Range: -0.7105

Max Act: 0.7105. Min Act: -0.0001

Data Index: 248955 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6809. Min Act: -0.0001

Data Index: 607059 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6677. Min Act: -0.0001

Data Index: 451890 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6633. Min Act: -0.0001

Data Index: 1037151 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6428. Min Act: -0.0001

Data Index: 1277842 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6757. Min Act: -0.0001

Data Index: 874445 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6486. Min Act: -0.0001

Data Index: 295927 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6276. Min Act: -0.0001

Data Index: 304403 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6540. Min Act: -0.0001

Data Index: 914681 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6372. Min Act: -0.0001

Data Index: 1031914 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5975. Min Act: -0.0001

Data Index: 1184689 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6538. Min Act: -0.0001

Data Index: 1183811 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6531. Min Act: -0.0001

Data Index: 292944 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6583. Min Act: -0.0001

Data Index: 1173634 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6342. Min Act: -0.0001

Data Index: 983388 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6203. Min Act: -0.0001

Data Index: 16225 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6159. Min Act: -0.0001

Data Index: 1221427 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5764. Min Act: -0.0001

Data Index: 420249 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6107. Min Act: -0.0001

Data Index: 99659 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6000. Min Act: -0.0001

Data Index: 90978 (C4 (Web Text))

Max Activating Token Index: 495