Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.8131. Min Act: -0.1700
Data Index: 2396973 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.7506. Min Act: -0.1700
Data Index: 1695827 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.7506. Min Act: -0.1700
Data Index: 6161966 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.6881. Min Act: -0.1700
Data Index: 1277708 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.6256. Min Act: -0.1700
Data Index: 8799311 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.5631. Min Act: -0.1700
Data Index: 1096445 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.5318. Min Act: -0.1700
Data Index: 6679730 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.5631. Min Act: -0.1700
Data Index: 4246268 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.5006. Min Act: -0.1700
Data Index: 139240 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4693. Min Act: -0.1700
Data Index: 5698747 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4693. Min Act: -0.1700
Data Index: 7024642 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4381. Min Act: -0.1700
Data Index: 3504047 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4381. Min Act: -0.1700
Data Index: 8516216 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4381. Min Act: -0.1700
Data Index: 7128553 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4068. Min Act: -0.1700
Data Index: 2173564 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4068. Min Act: -0.1700
Data Index: 6735654 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4068. Min Act: -0.1700
Data Index: 3590578 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4068. Min Act: -0.1700
Data Index: 4154040 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4068. Min Act: -0.1700
Data Index: 7072888 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8131. Min Range: -7.8131
Max Act: 7.4068. Min Act: -0.1700
Data Index: 742406 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19