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

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

Neuron 616 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: 4.6685. Min Range: -4.6685

Max Act: 4.6685. Min Act: -0.1700

Data Index: 1099836 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.5950. Min Act: -0.1700

Data Index: 464142 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.4732. Min Act: -0.1700

Data Index: 8944 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.4628. Min Act: -0.1700

Data Index: 1275675 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.3976. Min Act: -0.1700

Data Index: 1192022 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.4138. Min Act: -0.1700

Data Index: 879423 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.3698. Min Act: -0.1700

Data Index: 557689 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.3778. Min Act: -0.1700

Data Index: 810077 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.3518. Min Act: -0.1700

Data Index: 95040 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.3224. Min Act: -0.1700

Data Index: 456773 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.3200. Min Act: -0.1700

Data Index: 8216 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.3213. Min Act: -0.1699

Data Index: 760325 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.3304. Min Act: -0.1699

Data Index: 197483 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.2742. Min Act: -0.1700

Data Index: 469520 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.2882. Min Act: -0.1700

Data Index: 911694 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.2834. Min Act: -0.1700

Data Index: 10643 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.2751. Min Act: -0.1700

Data Index: 529206 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.2876. Min Act: -0.1700

Data Index: 3773 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.2997. Min Act: -0.1700

Data Index: 298099 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 4.6685. Min Range: -4.6685

Max Act: 4.2812. Min Act: -0.1698

Data Index: 1352512 (C4 (Web Text))

Max Activating Token Index: 1001