Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.1888. Min Act: -0.1700
Data Index: 1378188 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.1263. Min Act: -0.1700
Data Index: 5905980 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.1575. Min Act: -0.1700
Data Index: 5866364 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.0950. Min Act: -0.1700
Data Index: 6319019 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.0638. Min Act: -0.1700
Data Index: 8035965 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.0325. Min Act: -0.1700
Data Index: 601129 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.0013. Min Act: -0.1700
Data Index: 3614365 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.0013. Min Act: -0.1700
Data Index: 7012206 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1888. Min Range: -6.1888
Max Act: 6.0013. Min Act: -0.1700
Data Index: 831303 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9388. Min Act: -0.1700
Data Index: 699805 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9700. Min Act: -0.1700
Data Index: 2770992 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9700. Min Act: -0.1700
Data Index: 5674658 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9388. Min Act: -0.1700
Data Index: 1009561 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9388. Min Act: -0.1700
Data Index: 4432079 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9075. Min Act: -0.1700
Data Index: 2055202 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9075. Min Act: -0.1700
Data Index: 6194149 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9388. Min Act: -0.1700
Data Index: 5640220 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9075. Min Act: -0.1700
Data Index: 3802439 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9075. Min Act: -0.1700
Data Index: 6500464 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1888. Min Range: -6.1888
Max Act: 5.9075. Min Act: -0.1700
Data Index: 3278129 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19