Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4277 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.7790. Min Act: -0.1700
Data Index: 8645689 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.7477. Min Act: -0.1700
Data Index: 6772580 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.7477. Min Act: -0.1700
Data Index: 8100147 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6852. Min Act: -0.1700
Data Index: 4325636 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6852. Min Act: -0.1700
Data Index: 5546718 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6852. Min Act: -0.1700
Data Index: 4252232 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6539. Min Act: -0.1700
Data Index: 7917009 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6539. Min Act: -0.1700
Data Index: 108987 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6539. Min Act: -0.1700
Data Index: 5811410 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6539. Min Act: -0.1700
Data Index: 2473821 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6226. Min Act: -0.1700
Data Index: 852000 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6226. Min Act: -0.1700
Data Index: 8661186 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6226. Min Act: -0.1700
Data Index: 3742044 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6226. Min Act: -0.1700
Data Index: 8755382 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.6226. Min Act: -0.1700
Data Index: 7917010 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.5913. Min Act: -0.1700
Data Index: 4146423 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.5756. Min Act: -0.1700
Data Index: 8224011 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.5913. Min Act: -0.1700
Data Index: 5427387 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.5913. Min Act: -0.1700
Data Index: 3129649 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7790. Min Range: -3.7790
Max Act: 3.5913. Min Act: -0.1700
Data Index: 5029762 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19