Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.5808. Min Act: -0.1700
Data Index: 7369961 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.5183. Min Act: -0.1700
Data Index: 6973312 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.4871. Min Act: -0.1700
Data Index: 5092947 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.3933. Min Act: -0.1700
Data Index: 7233584 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.3308. Min Act: -0.1700
Data Index: 8825048 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.3308. Min Act: -0.1700
Data Index: 4082503 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.2996. Min Act: -0.1700
Data Index: 8440718 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.2996. Min Act: -0.1700
Data Index: 3329458 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.2996. Min Act: -0.1700
Data Index: 780396 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.2683. Min Act: -0.1700
Data Index: 3183515 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1746. Min Act: -0.1700
Data Index: 6712235 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1746. Min Act: -0.1700
Data Index: 6910809 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1746. Min Act: -0.1700
Data Index: 2352368 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1433. Min Act: -0.1700
Data Index: 7792685 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1433. Min Act: -0.1700
Data Index: 2765999 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1121. Min Act: -0.1700
Data Index: 5237050 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1433. Min Act: -0.1700
Data Index: 3685420 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1121. Min Act: -0.1700
Data Index: 1584780 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1121. Min Act: -0.1700
Data Index: 744995 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5808. Min Range: -6.5808
Max Act: 6.1121. Min Act: -0.1700
Data Index: 5210914 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19