Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5062 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0585. Min Range: -4.0585
Max Act: 4.0273. Min Act: -0.1700
Data Index: 3739183 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0585. Min Range: -4.0585
Max Act: 4.0273. Min Act: -0.1700
Data Index: 8832830 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0585. Min Range: -4.0585
Max Act: 4.0585. Min Act: -0.1700
Data Index: 5173029 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.9960. Min Act: -0.1700
Data Index: 7397015 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.9647. Min Act: -0.1700
Data Index: 5420506 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.9647. Min Act: -0.1700
Data Index: 900774 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.9022. Min Act: -0.1700
Data Index: 1482224 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.9335. Min Act: -0.1700
Data Index: 2408643 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.9335. Min Act: -0.1700
Data Index: 4747598 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.9022. Min Act: -0.1700
Data Index: 2238127 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.9022. Min Act: -0.1700
Data Index: 596915 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8709. Min Act: -0.1700
Data Index: 2445167 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8397. Min Act: -0.1700
Data Index: 4639295 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8709. Min Act: -0.1700
Data Index: 4748099 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8709. Min Act: -0.1700
Data Index: 8312391 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8397. Min Act: -0.1700
Data Index: 2595198 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8397. Min Act: -0.1700
Data Index: 4747596 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8397. Min Act: -0.1700
Data Index: 2120756 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8397. Min Act: -0.1700
Data Index: 6505002 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0585. Min Range: -4.0585
Max Act: 3.8397. Min Act: -0.1700
Data Index: 2188500 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19