Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4787 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.9520. Min Act: -0.1700
Data Index: 2476641 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.9520. Min Act: -0.1700
Data Index: 2410225 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.8583. Min Act: -0.1700
Data Index: 1887963 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.8583. Min Act: -0.1700
Data Index: 4099711 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.8895. Min Act: -0.1700
Data Index: 2364943 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.7645. Min Act: -0.1700
Data Index: 943161 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.7333. Min Act: -0.1700
Data Index: 3232846 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.7645. Min Act: -0.1700
Data Index: 6431704 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.7333. Min Act: -0.1700
Data Index: 7126166 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.6708. Min Act: -0.1700
Data Index: 6194737 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.6395. Min Act: -0.1700
Data Index: 2898570 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.7020. Min Act: -0.1700
Data Index: 3138476 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.6395. Min Act: -0.1700
Data Index: 3355778 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.6083. Min Act: -0.1700
Data Index: 5257839 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.6083. Min Act: -0.1700
Data Index: 353967 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.6083. Min Act: -0.1700
Data Index: 1220586 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.5770. Min Act: -0.1700
Data Index: 2449390 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.5770. Min Act: -0.1700
Data Index: 6581756 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.6083. Min Act: -0.1700
Data Index: 8230205 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9520. Min Range: -6.9520
Max Act: 6.5145. Min Act: -0.1700
Data Index: 421791 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19