Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.8917. Min Act: -0.1700
Data Index: 6263870 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.7979. Min Act: -0.1700
Data Index: 5515274 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.7354. Min Act: -0.1700
Data Index: 3971286 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.6729. Min Act: -0.1700
Data Index: 5444976 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.7042. Min Act: -0.1700
Data Index: 6098812 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.6729. Min Act: -0.1700
Data Index: 1200840 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.6729. Min Act: -0.1700
Data Index: 5252261 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.6729. Min Act: -0.1700
Data Index: 4556044 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.7042. Min Act: -0.1700
Data Index: 3487218 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.6417. Min Act: -0.1700
Data Index: 5534614 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.6417. Min Act: -0.1700
Data Index: 2960510 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5792. Min Act: -0.1700
Data Index: 1932680 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5792. Min Act: -0.1700
Data Index: 3406572 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5792. Min Act: -0.1700
Data Index: 534233 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5479. Min Act: -0.1700
Data Index: 7009675 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5479. Min Act: -0.1700
Data Index: 8053053 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5479. Min Act: -0.1700
Data Index: 7845475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5167. Min Act: -0.1700
Data Index: 4778638 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5167. Min Act: -0.1700
Data Index: 673753 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8917. Min Range: -6.8917
Max Act: 6.5167. Min Act: -0.1700
Data Index: 3748214 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19