Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2841 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1448. Min Range: -5.1448
Max Act: 5.1448. Min Act: -0.1700
Data Index: 1154522 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1448. Min Range: -5.1448
Max Act: 5.0511. Min Act: -0.1700
Data Index: 4627485 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1448. Min Range: -5.1448
Max Act: 5.0198. Min Act: -0.1700
Data Index: 1380462 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9886. Min Act: -0.1700
Data Index: 7417643 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9886. Min Act: -0.1700
Data Index: 6909873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9886. Min Act: -0.1700
Data Index: 8668730 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3259757 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9573. Min Act: -0.1700
Data Index: 6389169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9573. Min Act: -0.1700
Data Index: 3053961 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9573. Min Act: -0.1700
Data Index: 6466378 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9573. Min Act: -0.1698
Data Index: 3813061 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8948. Min Act: -0.1681
Data Index: 1879332 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8948. Min Act: -0.1700
Data Index: 4503890 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9261. Min Act: -0.1699
Data Index: 1280739 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8948. Min Act: -0.1699
Data Index: 1200914 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.9573. Min Act: -0.1700
Data Index: 5373176 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8948. Min Act: -0.1700
Data Index: 3367071 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8948. Min Act: -0.1700
Data Index: 5218189 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8948. Min Act: -0.1700
Data Index: 5559595 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1448. Min Range: -5.1448
Max Act: 4.8323. Min Act: -0.1693
Data Index: 3759274 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19