Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5129 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0284. Min Range: -8.0284
Max Act: 8.0284. Min Act: -0.1700
Data Index: 4257225 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.4972. Min Act: -0.1700
Data Index: 7437480 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.4347. Min Act: -0.1700
Data Index: 4526494 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.2784. Min Act: -0.1700
Data Index: 8688541 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.2472. Min Act: -0.1700
Data Index: 3786733 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.2159. Min Act: -0.1700
Data Index: 1142949 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.2159. Min Act: -0.1700
Data Index: 3483728 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.2472. Min Act: -0.1700
Data Index: 4449881 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.1222. Min Act: -0.1700
Data Index: 1460142 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.1222. Min Act: -0.1700
Data Index: 6570351 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0284. Min Range: -8.0284
Max Act: 7.0597. Min Act: -0.1700
Data Index: 3923672 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.9972. Min Act: -0.1700
Data Index: 3368167 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.9972. Min Act: -0.1700
Data Index: 6427054 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.9972. Min Act: -0.1700
Data Index: 2248547 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.9347. Min Act: -0.1700
Data Index: 2450735 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.9034. Min Act: -0.1700
Data Index: 3483729 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.9034. Min Act: -0.1700
Data Index: 844152 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.8722. Min Act: -0.1700
Data Index: 4277849 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.8722. Min Act: -0.1700
Data Index: 685577 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0284. Min Range: -8.0284
Max Act: 6.8097. Min Act: -0.1700
Data Index: 5096368 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19