Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.5456. Min Act: -0.1700
Data Index: 7308457 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.2643. Min Act: -0.1700
Data Index: 6162215 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.2018. Min Act: -0.1700
Data Index: 6804472 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.2018. Min Act: -0.1700
Data Index: 1093937 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.1393. Min Act: -0.1700
Data Index: 5033440 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.1393. Min Act: -0.1700
Data Index: 1096704 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0768. Min Act: -0.1700
Data Index: 589086 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0768. Min Act: -0.1700
Data Index: 415960 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0768. Min Act: -0.1700
Data Index: 4710234 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0768. Min Act: -0.1700
Data Index: 1806465 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0768. Min Act: -0.1700
Data Index: 1612609 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0768. Min Act: -0.1700
Data Index: 4614724 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0456. Min Act: -0.1700
Data Index: 6202648 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0143. Min Act: -0.1700
Data Index: 6902489 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0143. Min Act: -0.1700
Data Index: 7554153 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0456. Min Act: -0.1700
Data Index: 1364990 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5456. Min Range: -5.5456
Max Act: 5.0456. Min Act: -0.1700
Data Index: 5110278 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5456. Min Range: -5.5456
Max Act: 4.9831. Min Act: -0.1700
Data Index: 4849692 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5456. Min Range: -5.5456
Max Act: 4.9831. Min Act: -0.1700
Data Index: 3995978 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5456. Min Range: -5.5456
Max Act: 4.9518. Min Act: -0.1700
Data Index: 3830933 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19