Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1900 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.3588. Min Act: -0.1700

Data Index: 624989 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.3517. Min Act: -0.1700

Data Index: 159218 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.3330. Min Act: -0.1700

Data Index: 1030159 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.3406. Min Act: -0.1700

Data Index: 1124024 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.3488. Min Act: -0.1700

Data Index: 880318 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2957. Min Act: -0.1700

Data Index: 1245908 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2886. Min Act: -0.1700

Data Index: 224131 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2932. Min Act: -0.1700

Data Index: 217642 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2933. Min Act: -0.1700

Data Index: 100636 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2784. Min Act: -0.1700

Data Index: 1293071 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2817. Min Act: -0.1700

Data Index: 162886 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2443. Min Act: -0.1700

Data Index: 1197121 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2526. Min Act: -0.1700

Data Index: 854014 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2348. Min Act: -0.1700

Data Index: 633308 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2298. Min Act: -0.1700

Data Index: 848460 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2574. Min Act: -0.1700

Data Index: 1040313 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2638. Min Act: -0.1700

Data Index: 452006 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2506. Min Act: -0.1700

Data Index: 852939 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2265. Min Act: -0.1700

Data Index: 678404 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 4.3588. Min Range: -4.3588

Max Act: 4.2339. Min Act: -0.1700

Data Index: 468096 (C4 (Web Text))

Max Activating Token Index: 752