Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.6002. Min Act: -0.1700
Data Index: 29190 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.5065. Min Act: -0.1700
Data Index: 6737450 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.4127. Min Act: -0.1700
Data Index: 7991759 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.2565. Min Act: -0.1700
Data Index: 1992111 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.2565. Min Act: -0.1700
Data Index: 6813891 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.2252. Min Act: -0.1700
Data Index: 1435948 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.2252. Min Act: -0.1700
Data Index: 7168025 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.2252. Min Act: -0.1700
Data Index: 4137979 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1940. Min Act: -0.1700
Data Index: 6243724 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1940. Min Act: -0.1700
Data Index: 6857720 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1940. Min Act: -0.1700
Data Index: 4559859 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1627. Min Act: -0.1700
Data Index: 5041460 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1627. Min Act: -0.1700
Data Index: 4243730 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1315. Min Act: -0.1700
Data Index: 4013388 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1627. Min Act: -0.1700
Data Index: 3848964 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1315. Min Act: -0.1700
Data Index: 7038815 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1315. Min Act: -0.1700
Data Index: 89164 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1627. Min Act: -0.1700
Data Index: 3802762 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1002. Min Act: -0.1700
Data Index: 2860702 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6002. Min Range: -5.6002
Max Act: 5.1002. Min Act: -0.1700
Data Index: 5278230 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19