Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5026 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.8780. Min Act: -0.1700
Data Index: 3583835 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.6280. Min Act: -0.1700
Data Index: 2328733 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.4718. Min Act: -0.1700
Data Index: 8112493 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.3780. Min Act: -0.1700
Data Index: 2214113 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.4093. Min Act: -0.1700
Data Index: 3433158 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.3468. Min Act: -0.1700
Data Index: 5330303 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.3155. Min Act: -0.1700
Data Index: 6381799 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.2843. Min Act: -0.1700
Data Index: 5067130 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.2843. Min Act: -0.1700
Data Index: 3990142 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.2530. Min Act: -0.1700
Data Index: 4904303 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.1280. Min Act: -0.1700
Data Index: 2149480 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.1593. Min Act: -0.1700
Data Index: 250033 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.1280. Min Act: -0.1700
Data Index: 77909 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.0655. Min Act: -0.1700
Data Index: 8050369 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.0030. Min Act: -0.1700
Data Index: 7530478 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8780. Min Range: -7.8780
Max Act: 7.0030. Min Act: -0.1700
Data Index: 5704279 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8780. Min Range: -7.8780
Max Act: 6.9718. Min Act: -0.1700
Data Index: 4060340 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8780. Min Range: -7.8780
Max Act: 6.9718. Min Act: -0.1700
Data Index: 1122644 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8780. Min Range: -7.8780
Max Act: 6.9093. Min Act: -0.1700
Data Index: 607993 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8780. Min Range: -7.8780
Max Act: 6.8468. Min Act: -0.1700
Data Index: 2163764 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19