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

Dataset: Open Web Text

Neuron 2312 in Layer 4

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: 6.7112. Min Range: -6.7112

Max Act: 6.7069. Min Act: -0.1700

Data Index: 2449918 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.7112. Min Act: -0.1700

Data Index: 4091082 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.6463. Min Act: -0.1700

Data Index: 309622 (Open Web Text)

Max Activating Token Index: 364

Text #3

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.5504. Min Act: -0.1700

Data Index: 4025399 (Open Web Text)

Max Activating Token Index: 796

Text #4

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.5387. Min Act: -0.1700

Data Index: 6951671 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.4525. Min Act: -0.1700

Data Index: 3185195 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.4632. Min Act: -0.1700

Data Index: 4872558 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.4601. Min Act: -0.1700

Data Index: 2221320 (Open Web Text)

Max Activating Token Index: 643

Text #8

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.4494. Min Act: -0.1700

Data Index: 8658927 (Open Web Text)

Max Activating Token Index: 275

Text #9

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.4678. Min Act: -0.1700

Data Index: 7455999 (Open Web Text)

Max Activating Token Index: 950

Text #10

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.4521. Min Act: -0.1700

Data Index: 3396363 (Open Web Text)

Max Activating Token Index: 967

Text #11

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.4198. Min Act: -0.1700

Data Index: 7442022 (Open Web Text)

Max Activating Token Index: 352

Text #12

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.3929. Min Act: -0.1700

Data Index: 5548477 (Open Web Text)

Max Activating Token Index: 954

Text #13

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.2934. Min Act: -0.1700

Data Index: 7868354 (Open Web Text)

Max Activating Token Index: 290

Text #14

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.3970. Min Act: -0.1700

Data Index: 7588286 (Open Web Text)

Max Activating Token Index: 289

Text #15

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.3136. Min Act: -0.1700

Data Index: 850673 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.3311. Min Act: -0.1700

Data Index: 3969791 (Open Web Text)

Max Activating Token Index: 392

Text #17

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.2973. Min Act: -0.1700

Data Index: 7031728 (Open Web Text)

Max Activating Token Index: 957

Text #18

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.3054. Min Act: -0.1700

Data Index: 5660427 (Open Web Text)

Max Activating Token Index: 285

Text #19

Max Range: 6.7112. Min Range: -6.7112

Max Act: 6.3076. Min Act: -0.1700

Data Index: 2187777 (Open Web Text)

Max Activating Token Index: 954