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

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

Neuron 2632 in Layer 0

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: 0.0567. Min Range: -0.0567

Max Act: 0.0560. Min Act: -0.0001

Data Index: 735783 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0001

Data Index: 178082 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0544. Min Act: -0.0001

Data Index: 236747 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0537. Min Act: -0.0001

Data Index: 264793 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0543. Min Act: -0.0001

Data Index: 936166 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0539. Min Act: -0.0001

Data Index: 759327 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1288188 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0532. Min Act: -0.0001

Data Index: 456796 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0539. Min Act: -0.0001

Data Index: 1317695 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0539. Min Act: -0.0001

Data Index: 127587 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0537. Min Act: -0.0001

Data Index: 206386 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0531. Min Act: -0.0001

Data Index: 228026 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0537. Min Act: -0.0001

Data Index: 771406 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0526. Min Act: -0.0001

Data Index: 207492 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1201803 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0519. Min Act: -0.0001

Data Index: 481453 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0510. Min Act: -0.0001

Data Index: 541552 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0511. Min Act: -0.0001

Data Index: 2107 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0523. Min Act: -0.0001

Data Index: 281847 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0507. Min Act: -0.0001

Data Index: 436400 (C4 (Web Text))

Max Activating Token Index: 205