Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 478 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.7117. Min Act: -0.1700
Data Index: 1534893 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.7429. Min Act: -0.1700
Data Index: 2723929 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.7117. Min Act: -0.1700
Data Index: 3629309 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.6804. Min Act: -0.1700
Data Index: 5896170 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.6804. Min Act: -0.1700
Data Index: 6271645 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.6179. Min Act: -0.1700
Data Index: 7671204 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5554. Min Act: -0.1700
Data Index: 5083901 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5554. Min Act: -0.1700
Data Index: 5300187 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5554. Min Act: -0.1700
Data Index: 2478735 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5554. Min Act: -0.1700
Data Index: 2665114 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5554. Min Act: -0.1700
Data Index: 2190736 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5554. Min Act: -0.1700
Data Index: 6202587 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5242. Min Act: -0.1700
Data Index: 278113 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5242. Min Act: -0.1700
Data Index: 688055 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5242. Min Act: -0.1700
Data Index: 2753433 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.4929. Min Act: -0.1700
Data Index: 791095 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.4929. Min Act: -0.1700
Data Index: 6139953 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.4929. Min Act: -0.1700
Data Index: 6974062 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.5242. Min Act: -0.1700
Data Index: 7400878 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7429. Min Range: -5.7429
Max Act: 5.4929. Min Act: -0.1700
Data Index: 5907022 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19