Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2716 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.7479. Min Act: -0.1700
Data Index: 4366065 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.7167. Min Act: -0.1700
Data Index: 7530341 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.7167. Min Act: -0.1700
Data Index: 789403 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.7479. Min Act: -0.1700
Data Index: 7339954 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.7167. Min Act: -0.1700
Data Index: 1232578 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4979. Min Act: -0.1700
Data Index: 8345408 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.5292. Min Act: -0.1700
Data Index: 8034908 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.5292. Min Act: -0.1700
Data Index: 6402162 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4979. Min Act: -0.1700
Data Index: 5309454 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4667. Min Act: -0.1700
Data Index: 4111010 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4667. Min Act: -0.1700
Data Index: 1389381 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4667. Min Act: -0.1700
Data Index: 2705154 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4667. Min Act: -0.1700
Data Index: 7631943 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4354. Min Act: -0.1700
Data Index: 601740 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4354. Min Act: -0.1700
Data Index: 1587282 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4042. Min Act: -0.1700
Data Index: 4500594 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4042. Min Act: -0.1700
Data Index: 7522456 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4042. Min Act: -0.1700
Data Index: 4439163 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4042. Min Act: -0.1700
Data Index: 2175692 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7479. Min Range: -5.7479
Max Act: 5.4042. Min Act: -0.1700
Data Index: 8700320 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19