Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1565 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0132. Min Range: -4.0132
Max Act: 4.0132. Min Act: -0.1700
Data Index: 1239767 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.8569. Min Act: -0.1700
Data Index: 5047171 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.8569. Min Act: -0.1700
Data Index: 317149 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7943. Min Act: -0.1700
Data Index: 8498385 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.8256. Min Act: -0.1700
Data Index: 7058903 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.8256. Min Act: -0.1700
Data Index: 4928570 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.8256. Min Act: -0.1700
Data Index: 2589525 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7943. Min Act: -0.1700
Data Index: 4831120 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7943. Min Act: -0.1700
Data Index: 2261367 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7631. Min Act: -0.1700
Data Index: 6408951 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.8256. Min Act: -0.1700
Data Index: 2445706 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7631. Min Act: -0.1700
Data Index: 1485159 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7943. Min Act: -0.1700
Data Index: 4580389 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7631. Min Act: -0.1700
Data Index: 2043702 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7631. Min Act: -0.1700
Data Index: 8502031 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7318. Min Act: -0.1700
Data Index: 6293703 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7318. Min Act: -0.1700
Data Index: 5801696 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7318. Min Act: -0.1700
Data Index: 7930287 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7318. Min Act: -0.1700
Data Index: 4591779 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0132. Min Range: -4.0132
Max Act: 3.7318. Min Act: -0.1700
Data Index: 4610125 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19