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

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

Neuron 2183 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: 0.7960. Min Range: -0.7960

Max Act: 0.7680. Min Act: -0.0001

Data Index: 1097021 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.7960. Min Act: -0.0001

Data Index: 58133 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.7771. Min Act: -0.0001

Data Index: 822859 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.7584. Min Act: -0.0001

Data Index: 443798 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.7329. Min Act: -0.0001

Data Index: 223565 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.7061. Min Act: -0.0001

Data Index: 429592 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.7456. Min Act: -0.0001

Data Index: 653747 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.7226. Min Act: -0.0001

Data Index: 1357516 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6674. Min Act: -0.0001

Data Index: 33766 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6839. Min Act: -0.0001

Data Index: 1342283 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6330. Min Act: -0.0001

Data Index: 773246 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1191272 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6235. Min Act: -0.0001

Data Index: 822447 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6825. Min Act: -0.0001

Data Index: 596883 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6353. Min Act: -0.0001

Data Index: 1185853 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6158. Min Act: -0.0001

Data Index: 737552 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6743. Min Act: -0.0001

Data Index: 278592 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6847. Min Act: -0.0001

Data Index: 1310081 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1153034 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6701. Min Act: -0.0001

Data Index: 407845 (C4 (Web Text))

Max Activating Token Index: 264