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

Dataset: Open Web Text

Neuron 947 in Layer 5

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: 3.8942. Min Range: -3.8942

Max Act: 3.8942. Min Act: -0.1700

Data Index: 5840337 (Open Web Text)

Max Activating Token Index: 208

Text #1

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8645. Min Act: -0.1700

Data Index: 4250769 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8564. Min Act: -0.1700

Data Index: 2400823 (Open Web Text)

Max Activating Token Index: 367

Text #3

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.8235. Min Act: -0.1700

Data Index: 8222840 (Open Web Text)

Max Activating Token Index: 717

Text #4

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7197. Min Act: -0.1700

Data Index: 3624068 (Open Web Text)

Max Activating Token Index: 575

Text #5

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7420. Min Act: -0.1700

Data Index: 4715175 (Open Web Text)

Max Activating Token Index: 586

Text #6

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7488. Min Act: -0.1700

Data Index: 3504091 (Open Web Text)

Max Activating Token Index: 911

Text #7

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7424. Min Act: -0.1700

Data Index: 1581778 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6947. Min Act: -0.1700

Data Index: 4802703 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7136. Min Act: -0.1700

Data Index: 3436611 (Open Web Text)

Max Activating Token Index: 243

Text #10

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7015. Min Act: -0.1700

Data Index: 3742624 (Open Web Text)

Max Activating Token Index: 767

Text #11

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.7053. Min Act: -0.1700

Data Index: 3199195 (Open Web Text)

Max Activating Token Index: 522

Text #12

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6950. Min Act: -0.1700

Data Index: 5915511 (Open Web Text)

Max Activating Token Index: 352

Text #13

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6806. Min Act: -0.1700

Data Index: 7586475 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6952. Min Act: -0.1700

Data Index: 867044 (Open Web Text)

Max Activating Token Index: 383

Text #15

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6814. Min Act: -0.1700

Data Index: 4763221 (Open Web Text)

Max Activating Token Index: 634

Text #16

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6601. Min Act: -0.1700

Data Index: 7045965 (Open Web Text)

Max Activating Token Index: 792

Text #17

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6795. Min Act: -0.1700

Data Index: 1416156 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6473. Min Act: -0.1700

Data Index: 4405785 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 3.8942. Min Range: -3.8942

Max Act: 3.6593. Min Act: -0.1700

Data Index: 2616581 (Open Web Text)

Max Activating Token Index: 832