Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.9573. Min Act: -0.1700
Data Index: 2912851 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.8948. Min Act: -0.1700
Data Index: 5441650 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.6760. Min Act: -0.1700
Data Index: 454279 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.4885. Min Act: -0.1700
Data Index: 2912853 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.5510. Min Act: -0.1700
Data Index: 6096873 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.4260. Min Act: -0.1700
Data Index: 4844069 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.1760. Min Act: -0.1700
Data Index: 2502203 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.3010. Min Act: -0.1700
Data Index: 5929988 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.2073. Min Act: -0.1700
Data Index: 267110 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.1760. Min Act: -0.1700
Data Index: 314271 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.1448. Min Act: -0.1700
Data Index: 2265730 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.1760. Min Act: -0.1700
Data Index: 488177 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.1135. Min Act: -0.1700
Data Index: 5730497 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.1448. Min Act: -0.1700
Data Index: 5226131 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.0823. Min Act: -0.1700
Data Index: 204225 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.1135. Min Act: -0.1700
Data Index: 1281473 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.0198. Min Act: -0.1700
Data Index: 2752635 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.0198. Min Act: -0.1700
Data Index: 6842373 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.0510. Min Act: -0.1700
Data Index: 5631494 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9573. Min Range: -6.9573
Max Act: 6.0198. Min Act: -0.1700
Data Index: 1508694 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19