Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3031 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.7211. Min Act: -0.1700
Data Index: 3517751 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.5336. Min Act: -0.1700
Data Index: 8261481 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.4711. Min Act: -0.1700
Data Index: 6256692 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.4711. Min Act: -0.1700
Data Index: 8575495 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.4398. Min Act: -0.1700
Data Index: 6008485 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.3773. Min Act: -0.1700
Data Index: 73676 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.3461. Min Act: -0.1700
Data Index: 7051648 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.3148. Min Act: -0.1700
Data Index: 7605261 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.3461. Min Act: -0.1700
Data Index: 6335505 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.3461. Min Act: -0.1700
Data Index: 4757156 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.3148. Min Act: -0.1700
Data Index: 4888325 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.2836. Min Act: -0.1700
Data Index: 6247853 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.2836. Min Act: -0.1700
Data Index: 992282 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.3148. Min Act: -0.1700
Data Index: 7687975 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.3148. Min Act: -0.1700
Data Index: 8075987 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.2836. Min Act: -0.1700
Data Index: 4838552 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.2836. Min Act: -0.1700
Data Index: 2300636 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.2523. Min Act: -0.1700
Data Index: 425622 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.2211. Min Act: -0.1700
Data Index: 4256982 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7211. Min Range: -6.7211
Max Act: 6.2211. Min Act: -0.1700
Data Index: 6370465 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19