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

Dataset: Open Web Text

Neuron 753 in Layer 2

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: 4.5787. Min Range: -4.5787

Max Act: 4.5787. Min Act: -0.1700

Data Index: 4294325 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.5680. Min Act: -0.1700

Data Index: 2800265 (Open Web Text)

Max Activating Token Index: 200

Text #2

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.5186. Min Act: -0.1700

Data Index: 5579523 (Open Web Text)

Max Activating Token Index: 506

Text #3

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.5136. Min Act: -0.1700

Data Index: 5196790 (Open Web Text)

Max Activating Token Index: 582

Text #4

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.5206. Min Act: -0.1700

Data Index: 4837245 (Open Web Text)

Max Activating Token Index: 147

Text #5

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4845. Min Act: -0.1700

Data Index: 2732748 (Open Web Text)

Max Activating Token Index: 347

Text #6

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4815. Min Act: -0.1700

Data Index: 6153275 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4868. Min Act: -0.1700

Data Index: 1272020 (Open Web Text)

Max Activating Token Index: 128

Text #8

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4461. Min Act: -0.1700

Data Index: 1416630 (Open Web Text)

Max Activating Token Index: 372

Text #9

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4580. Min Act: -0.1700

Data Index: 1648606 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4731. Min Act: -0.1700

Data Index: 885071 (Open Web Text)

Max Activating Token Index: 248

Text #11

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4751. Min Act: -0.1700

Data Index: 5863850 (Open Web Text)

Max Activating Token Index: 112

Text #12

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4591. Min Act: -0.1700

Data Index: 1017460 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4455. Min Act: -0.1700

Data Index: 5487730 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4315. Min Act: -0.1700

Data Index: 983035 (Open Web Text)

Max Activating Token Index: 242

Text #15

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4211. Min Act: -0.1700

Data Index: 3582984 (Open Web Text)

Max Activating Token Index: 886

Text #16

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.3964. Min Act: -0.1700

Data Index: 2920599 (Open Web Text)

Max Activating Token Index: 388

Text #17

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4261. Min Act: -0.1700

Data Index: 4772029 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4041. Min Act: -0.1700

Data Index: 7603923 (Open Web Text)

Max Activating Token Index: 850

Text #19

Max Range: 4.5787. Min Range: -4.5787

Max Act: 4.4359. Min Act: -0.1700

Data Index: 4231932 (Open Web Text)

Max Activating Token Index: 109