Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4347. Min Range: -8.4347
Max Act: 8.3097. Min Act: -0.1700
Data Index: 6341689 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4347. Min Range: -8.4347
Max Act: 8.4347. Min Act: -0.1700
Data Index: 6348628 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4347. Min Range: -8.4347
Max Act: 8.2472. Min Act: -0.1700
Data Index: 5688991 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4347. Min Range: -8.4347
Max Act: 8.0597. Min Act: -0.1700
Data Index: 7421685 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4347. Min Range: -8.4347
Max Act: 8.0597. Min Act: -0.1700
Data Index: 8095091 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4347. Min Range: -8.4347
Max Act: 8.1222. Min Act: -0.1700
Data Index: 7157443 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9972. Min Act: -0.1700
Data Index: 7393849 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9972. Min Act: -0.1700
Data Index: 4871143 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9972. Min Act: -0.1700
Data Index: 1793225 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9347. Min Act: -0.1700
Data Index: 4165700 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9972. Min Act: -0.1700
Data Index: 2786354 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9972. Min Act: -0.1700
Data Index: 2310407 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.8722. Min Act: -0.1700
Data Index: 5845258 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9347. Min Act: -0.1700
Data Index: 4499224 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9347. Min Act: -0.1700
Data Index: 2771084 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.9347. Min Act: -0.1700
Data Index: 2807273 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.8722. Min Act: -0.1700
Data Index: 4282324 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.8722. Min Act: -0.1700
Data Index: 4106469 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.8722. Min Act: -0.1700
Data Index: 8308790 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4347. Min Range: -8.4347
Max Act: 7.8097. Min Act: -0.1700
Data Index: 936021 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19