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

Dataset: Open Web Text

Neuron 55 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: 7.3003. Min Range: -7.3003

Max Act: 7.3003. Min Act: -0.1700

Data Index: 2264148 (Open Web Text)

Max Activating Token Index: 927

Text #1

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.8492. Min Act: -0.1700

Data Index: 8316844 (Open Web Text)

Max Activating Token Index: 842

Text #2

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.8863. Min Act: -0.1700

Data Index: 1661487 (Open Web Text)

Max Activating Token Index: 252

Text #3

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.8664. Min Act: -0.1700

Data Index: 2294926 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.6946. Min Act: -0.1700

Data Index: 8317875 (Open Web Text)

Max Activating Token Index: 680

Text #5

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.6202. Min Act: -0.1700

Data Index: 3444578 (Open Web Text)

Max Activating Token Index: 166

Text #6

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.4972. Min Act: -0.1700

Data Index: 4326042 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.4440. Min Act: -0.1698

Data Index: 8517963 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.4117. Min Act: -0.1700

Data Index: 3848422 (Open Web Text)

Max Activating Token Index: 376

Text #9

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.4128. Min Act: -0.1700

Data Index: 5846411 (Open Web Text)

Max Activating Token Index: 850

Text #10

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.3825. Min Act: -0.1700

Data Index: 8170043 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.4170. Min Act: -0.1700

Data Index: 2563130 (Open Web Text)

Max Activating Token Index: 223

Text #12

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.4119. Min Act: -0.1700

Data Index: 4550020 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.4238. Min Act: -0.1700

Data Index: 4528831 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.3356. Min Act: -0.1700

Data Index: 621125 (Open Web Text)

Max Activating Token Index: 465

Text #15

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.2813. Min Act: -0.1700

Data Index: 8588192 (Open Web Text)

Max Activating Token Index: 954

Text #16

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.2432. Min Act: -0.1700

Data Index: 6396890 (Open Web Text)

Max Activating Token Index: 280

Text #17

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.2735. Min Act: -0.1700

Data Index: 651639 (Open Web Text)

Max Activating Token Index: 250

Text #18

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.2505. Min Act: -0.1700

Data Index: 7090333 (Open Web Text)

Max Activating Token Index: 421

Text #19

Max Range: 7.3003. Min Range: -7.3003

Max Act: 6.1725. Min Act: -0.1700

Data Index: 1789358 (Open Web Text)

Max Activating Token Index: 87