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

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

Neuron 307 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: 3.2228. Min Range: -3.2228

Max Act: 3.2228. Min Act: -0.1700

Data Index: 317429 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.1145. Min Act: -0.1700

Data Index: 437275 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.1036. Min Act: -0.1699

Data Index: 674463 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.1091. Min Act: -0.1700

Data Index: 975223 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0860. Min Act: -0.1700

Data Index: 596104 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0932. Min Act: -0.1700

Data Index: 870540 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0794. Min Act: -0.1699

Data Index: 861715 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0535. Min Act: -0.1700

Data Index: 421706 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0658. Min Act: -0.1700

Data Index: 389386 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0546. Min Act: -0.1700

Data Index: 1305835 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0544. Min Act: -0.1700

Data Index: 817144 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0353. Min Act: -0.1700

Data Index: 753522 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0322. Min Act: -0.1700

Data Index: 1344964 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0349. Min Act: -0.1699

Data Index: 42499 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0351. Min Act: -0.1700

Data Index: 930769 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0386. Min Act: -0.1700

Data Index: 750029 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0478. Min Act: -0.1700

Data Index: 938467 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0359. Min Act: -0.1700

Data Index: 1110394 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0324. Min Act: -0.1700

Data Index: 1642247 (Python Code)

Max Activating Token Index: 913

Text #19

Max Range: 3.2228. Min Range: -3.2228

Max Act: 3.0278. Min Act: -0.1700

Data Index: 450915 (C4 (Web Text))

Max Activating Token Index: 15