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

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

Neuron 1465 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: 3.8122. Min Range: -3.8122

Max Act: 3.8122. Min Act: -0.1700

Data Index: 1071428 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.6088. Min Act: -0.1700

Data Index: 1173433 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.5148. Min Act: -0.1700

Data Index: 313290 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4991. Min Act: -0.1700

Data Index: 878685 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4835. Min Act: -0.1700

Data Index: 617985 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4521. Min Act: -0.1700

Data Index: 975292 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4365. Min Act: -0.1700

Data Index: 1257889 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4208. Min Act: -0.1700

Data Index: 1078184 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4208. Min Act: -0.1700

Data Index: 273682 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4051. Min Act: -0.1700

Data Index: 835879 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4051. Min Act: -0.1700

Data Index: 1104652 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.3894. Min Act: -0.1700

Data Index: 365096 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.4051. Min Act: -0.1700

Data Index: 811362 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.3894. Min Act: -0.1700

Data Index: 155322 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.3894. Min Act: -0.1700

Data Index: 307222 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.3737. Min Act: -0.1700

Data Index: 378837 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.3894. Min Act: -0.1700

Data Index: 37424 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.3737. Min Act: -0.1700

Data Index: 1113575 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.3737. Min Act: -0.1700

Data Index: 82346 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 3.8122. Min Range: -3.8122

Max Act: 3.3737. Min Act: -0.1700

Data Index: 793077 (C4 (Web Text))

Max Activating Token Index: 676