Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1617 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0741. Min Range: -6.0741
Max Act: 6.0741. Min Act: -0.1700
Data Index: 5961038 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0741. Min Range: -6.0741
Max Act: 6.0741. Min Act: -0.1700
Data Index: 847022 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0741. Min Range: -6.0741
Max Act: 6.0116. Min Act: -0.1700
Data Index: 3585839 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9804. Min Act: -0.1700
Data Index: 8085178 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9804. Min Act: -0.1700
Data Index: 2442014 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9491. Min Act: -0.1700
Data Index: 3304542 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9804. Min Act: -0.1700
Data Index: 4348959 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9491. Min Act: -0.1700
Data Index: 5557756 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9179. Min Act: -0.1700
Data Index: 3144157 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9491. Min Act: -0.1700
Data Index: 3778738 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9179. Min Act: -0.1700
Data Index: 4196064 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9179. Min Act: -0.1700
Data Index: 7764174 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.9179. Min Act: -0.1700
Data Index: 1543917 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.8554. Min Act: -0.1700
Data Index: 3428254 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.8241. Min Act: -0.1700
Data Index: 4354111 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.8554. Min Act: -0.1700
Data Index: 1027361 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.8241. Min Act: -0.1700
Data Index: 5282027 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.7616. Min Act: -0.1700
Data Index: 5244589 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.7929. Min Act: -0.1700
Data Index: 7621780 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0741. Min Range: -6.0741
Max Act: 5.7929. Min Act: -0.1700
Data Index: 6302628 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19