Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.7921. Min Act: -0.1700
Data Index: 6265499 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.7921. Min Act: -0.1700
Data Index: 1703915 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.7296. Min Act: -0.1700
Data Index: 6819047 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.6984. Min Act: -0.1700
Data Index: 3532953 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.6671. Min Act: -0.1700
Data Index: 6573849 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.6671. Min Act: -0.1700
Data Index: 6495366 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.6046. Min Act: -0.1700
Data Index: 2324010 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.6046. Min Act: -0.1700
Data Index: 4369937 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5734. Min Act: -0.1700
Data Index: 105691 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5734. Min Act: -0.1700
Data Index: 3349900 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5421. Min Act: -0.1700
Data Index: 932533 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5734. Min Act: -0.1700
Data Index: 5149232 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5421. Min Act: -0.1700
Data Index: 2975793 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5421. Min Act: -0.1700
Data Index: 425455 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5421. Min Act: -0.1700
Data Index: 931598 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5421. Min Act: -0.1700
Data Index: 695947 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5421. Min Act: -0.1700
Data Index: 5898195 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5421. Min Act: -0.1700
Data Index: 6807443 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5109. Min Act: -0.1700
Data Index: 598250 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7921. Min Range: -5.7921
Max Act: 5.5109. Min Act: -0.1700
Data Index: 6344738 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19