Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 722 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0874. Min Range: -4.0874
Max Act: 4.0874. Min Act: -0.1700
Data Index: 8272045 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.9936. Min Act: -0.1700
Data Index: 2240477 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.8998. Min Act: -0.1700
Data Index: 7963455 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.8998. Min Act: -0.1700
Data Index: 488852 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.8373. Min Act: -0.1700
Data Index: 5950837 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.8060. Min Act: -0.1700
Data Index: 850386 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.7747. Min Act: -0.1700
Data Index: 7361236 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.7747. Min Act: -0.1700
Data Index: 1591590 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.7747. Min Act: -0.1700
Data Index: 5446302 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.7121. Min Act: -0.1700
Data Index: 4852862 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.7278. Min Act: -0.1700
Data Index: 7975630 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.7121. Min Act: -0.1700
Data Index: 2238378 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.6965. Min Act: -0.1700
Data Index: 4414694 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.6965. Min Act: -0.1700
Data Index: 7710853 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.6965. Min Act: -0.1700
Data Index: 1016487 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.6809. Min Act: -0.1700
Data Index: 3490551 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.6809. Min Act: -0.1700
Data Index: 3798389 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.6652. Min Act: -0.1700
Data Index: 6844877 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.6652. Min Act: -0.1700
Data Index: 896087 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0874. Min Range: -4.0874
Max Act: 3.6809. Min Act: -0.1700
Data Index: 2493235 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19