Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2980 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.9599. Min Act: -0.1700

Data Index: 4642964 (Open Web Text)

Max Activating Token Index: 149

Text #1

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.7983. Min Act: -0.1700

Data Index: 4492735 (Open Web Text)

Max Activating Token Index: 117

Text #2

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.5812. Min Act: -0.1700

Data Index: 6153131 (Open Web Text)

Max Activating Token Index: 494

Text #3

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.5766. Min Act: -0.1699

Data Index: 6153140 (Open Web Text)

Max Activating Token Index: 651

Text #4

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.5220. Min Act: -0.1700

Data Index: 5367545 (Open Web Text)

Max Activating Token Index: 334

Text #5

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.5286. Min Act: -0.1700

Data Index: 1569614 (Open Web Text)

Max Activating Token Index: 84

Text #6

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4986. Min Act: -0.1700

Data Index: 197460 (Open Web Text)

Max Activating Token Index: 294

Text #7

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4959. Min Act: -0.1700

Data Index: 6153139 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4801. Min Act: -0.1700

Data Index: 6252537 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4904. Min Act: -0.1700

Data Index: 5814427 (Open Web Text)

Max Activating Token Index: 306

Text #10

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4540. Min Act: -0.1700

Data Index: 5814410 (Open Web Text)

Max Activating Token Index: 271

Text #11

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4422. Min Act: -0.1700

Data Index: 7710930 (Open Web Text)

Max Activating Token Index: 25

Text #12

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4393. Min Act: -0.1700

Data Index: 5814421 (Open Web Text)

Max Activating Token Index: 166

Text #13

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4521. Min Act: -0.1700

Data Index: 5814415 (Open Web Text)

Max Activating Token Index: 417

Text #14

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.3953. Min Act: -0.1698

Data Index: 6153127 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4190. Min Act: -0.1699

Data Index: 5814417 (Open Web Text)

Max Activating Token Index: 175

Text #16

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4063. Min Act: -0.1700

Data Index: 3073670 (Open Web Text)

Max Activating Token Index: 685

Text #17

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.3942. Min Act: -0.1700

Data Index: 5951748 (Open Web Text)

Max Activating Token Index: 317

Text #18

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.4140. Min Act: -0.1700

Data Index: 6153132 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 5.9599. Min Range: -5.9599

Max Act: 5.3812. Min Act: -0.1700

Data Index: 5367540 (Open Web Text)

Max Activating Token Index: 719