Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 842 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1146. Min Range: -3.1146

Max Act: 3.0831. Min Act: -0.1700

Data Index: 27013 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 3.1146. Min Range: -3.1146

Max Act: 3.1146. Min Act: -0.1699

Data Index: 1041429 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 3.1146. Min Range: -3.1146

Max Act: 3.0515. Min Act: -0.1700

Data Index: 1405332 (Python Code)

Max Activating Token Index: 415

Text #3

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9883. Min Act: -0.1699

Data Index: 1051431 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.8933. Min Act: -0.1700

Data Index: 1475921 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9409. Min Act: -0.1700

Data Index: 505394 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.9409. Min Act: -0.1700

Data Index: 965755 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.8933. Min Act: -0.1699

Data Index: 7706 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.8457. Min Act: -0.1700

Data Index: 356797 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7979. Min Act: -0.1700

Data Index: 187948 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7979. Min Act: -0.1700

Data Index: 151835 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7661. Min Act: -0.1700

Data Index: 224111 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7661. Min Act: -0.1700

Data Index: 1543680 (Python Code)

Max Activating Token Index: 530

Text #13

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7501. Min Act: -0.1700

Data Index: 692217 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7501. Min Act: -0.1700

Data Index: 92224 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7181. Min Act: -0.1700

Data Index: 185037 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7341. Min Act: -0.1700

Data Index: 259792 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7021. Min Act: -0.1700

Data Index: 1208000 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.7021. Min Act: -0.1700

Data Index: 1019115 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 3.1146. Min Range: -3.1146

Max Act: 2.6701. Min Act: -0.1700

Data Index: 445798 (C4 (Web Text))

Max Activating Token Index: 950