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

Dataset: Open Web Text

Neuron 803 in Layer 3

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: 4.4600. Min Range: -4.4600

Max Act: 4.4600. Min Act: -0.1700

Data Index: 6438714 (Open Web Text)

Max Activating Token Index: 758

Text #1

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.4408. Min Act: -0.1700

Data Index: 4786372 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.4296. Min Act: -0.1700

Data Index: 4121151 (Open Web Text)

Max Activating Token Index: 238

Text #3

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.4496. Min Act: -0.1700

Data Index: 8626420 (Open Web Text)

Max Activating Token Index: 323

Text #4

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.4271. Min Act: -0.1700

Data Index: 8215822 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.4082. Min Act: -0.1700

Data Index: 6559746 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.4083. Min Act: -0.1700

Data Index: 8035790 (Open Web Text)

Max Activating Token Index: 277

Text #7

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.3914. Min Act: -0.1700

Data Index: 874781 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.2806. Min Act: -0.1700

Data Index: 8215820 (Open Web Text)

Max Activating Token Index: 903

Text #9

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.3441. Min Act: -0.1700

Data Index: 1623566 (Open Web Text)

Max Activating Token Index: 598

Text #10

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.3280. Min Act: -0.1700

Data Index: 2816383 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.3327. Min Act: -0.1700

Data Index: 8086733 (Open Web Text)

Max Activating Token Index: 286

Text #12

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.3319. Min Act: -0.1700

Data Index: 1292716 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.2802. Min Act: -0.1700

Data Index: 6096068 (Open Web Text)

Max Activating Token Index: 246

Text #14

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.3181. Min Act: -0.1700

Data Index: 5955017 (Open Web Text)

Max Activating Token Index: 938

Text #15

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.2944. Min Act: -0.1700

Data Index: 5537093 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.2952. Min Act: -0.1700

Data Index: 532520 (Open Web Text)

Max Activating Token Index: 206

Text #17

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.3107. Min Act: -0.1700

Data Index: 7400890 (Open Web Text)

Max Activating Token Index: 231

Text #18

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.2906. Min Act: -0.1700

Data Index: 6421238 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 4.4600. Min Range: -4.4600

Max Act: 4.2613. Min Act: -0.1700

Data Index: 7662394 (Open Web Text)

Max Activating Token Index: 108