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

Dataset: Open Web Text

Neuron 92 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: 3.5935. Min Range: -3.5935

Max Act: 3.5935. Min Act: -0.1700

Data Index: 168814 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2996. Min Act: -0.1700

Data Index: 821100 (Open Web Text)

Max Activating Token Index: 193

Text #2

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2858. Min Act: -0.1700

Data Index: 1863514 (Open Web Text)

Max Activating Token Index: 339

Text #3

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2609. Min Act: -0.1700

Data Index: 594315 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2620. Min Act: -0.1700

Data Index: 7405525 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2861. Min Act: -0.1700

Data Index: 1874066 (Open Web Text)

Max Activating Token Index: 154

Text #6

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2381. Min Act: -0.1700

Data Index: 3100239 (Open Web Text)

Max Activating Token Index: 659

Text #7

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2567. Min Act: -0.1700

Data Index: 6436822 (Open Web Text)

Max Activating Token Index: 400

Text #8

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2677. Min Act: -0.1700

Data Index: 7913784 (Open Web Text)

Max Activating Token Index: 738

Text #9

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2171. Min Act: -0.1700

Data Index: 6903265 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2455. Min Act: -0.1700

Data Index: 3346321 (Open Web Text)

Max Activating Token Index: 658

Text #11

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2327. Min Act: -0.1700

Data Index: 3985291 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2363. Min Act: -0.1700

Data Index: 6006034 (Open Web Text)

Max Activating Token Index: 438

Text #13

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2213. Min Act: -0.1700

Data Index: 8318740 (Open Web Text)

Max Activating Token Index: 261

Text #14

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2092. Min Act: -0.1700

Data Index: 5907107 (Open Web Text)

Max Activating Token Index: 698

Text #15

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2103. Min Act: -0.1700

Data Index: 7804065 (Open Web Text)

Max Activating Token Index: 453

Text #16

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2076. Min Act: -0.1700

Data Index: 7398835 (Open Web Text)

Max Activating Token Index: 674

Text #17

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.1955. Min Act: -0.1700

Data Index: 8675761 (Open Web Text)

Max Activating Token Index: 524

Text #18

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.2310. Min Act: -0.1700

Data Index: 5756405 (Open Web Text)

Max Activating Token Index: 361

Text #19

Max Range: 3.5935. Min Range: -3.5935

Max Act: 3.1864. Min Act: -0.1700

Data Index: 2193380 (Open Web Text)

Max Activating Token Index: 977