Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.8700. Min Act: -0.1700
Data Index: 976230 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.7293. Min Act: -0.1700
Data Index: 8201317 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.5728. Min Act: -0.1700
Data Index: 7042318 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.5571. Min Act: -0.1700
Data Index: 8656339 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.5571. Min Act: -0.1700
Data Index: 196968 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4945. Min Act: -0.1700
Data Index: 7919889 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4945. Min Act: -0.1700
Data Index: 7158211 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4788. Min Act: -0.1700
Data Index: 3629696 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4788. Min Act: -0.1700
Data Index: 4725491 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4945. Min Act: -0.1700
Data Index: 6789839 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4788. Min Act: -0.1700
Data Index: 7165911 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4475. Min Act: -0.1700
Data Index: 1896620 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4318. Min Act: -0.1700
Data Index: 5947175 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4475. Min Act: -0.1700
Data Index: 749903 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4475. Min Act: -0.1700
Data Index: 5222604 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4162. Min Act: -0.1700
Data Index: 2367745 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4005. Min Act: -0.1700
Data Index: 5860998 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4162. Min Act: -0.1700
Data Index: 4087988 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.4005. Min Act: -0.1700
Data Index: 5592211 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8700. Min Range: -3.8700
Max Act: 3.3848. Min Act: -0.1700
Data Index: 4666052 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19