Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 94 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.7515. Min Act: -0.1700
Data Index: 5364284 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.6578. Min Act: -0.1700
Data Index: 3008161 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.6265. Min Act: -0.1700
Data Index: 2720698 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.6265. Min Act: -0.1700
Data Index: 8169530 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.5953. Min Act: -0.1700
Data Index: 2943440 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.5953. Min Act: -0.1700
Data Index: 6647040 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.5328. Min Act: -0.1700
Data Index: 352041 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.5015. Min Act: -0.1700
Data Index: 6296824 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.5015. Min Act: -0.1700
Data Index: 4203273 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.5015. Min Act: -0.1700
Data Index: 4799855 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4390. Min Act: -0.1700
Data Index: 7925241 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4703. Min Act: -0.1700
Data Index: 1944384 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4390. Min Act: -0.1700
Data Index: 4121030 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4390. Min Act: -0.1700
Data Index: 5838412 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4703. Min Act: -0.1700
Data Index: 6190719 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4390. Min Act: -0.1700
Data Index: 6361534 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4390. Min Act: -0.1700
Data Index: 6135079 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4390. Min Act: -0.1700
Data Index: 8828257 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4390. Min Act: -0.1700
Data Index: 7351366 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7515. Min Range: -5.7515
Max Act: 5.4390. Min Act: -0.1700
Data Index: 8079810 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19