Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1760 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0447. Min Range: -4.0447
Max Act: 4.0447. Min Act: -0.1700
Data Index: 2302659 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9196. Min Act: -0.1700
Data Index: 1322465 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.9196. Min Act: -0.1700
Data Index: 7781892 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8884. Min Act: -0.1700
Data Index: 1669597 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8884. Min Act: -0.1700
Data Index: 6806823 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8884. Min Act: -0.1700
Data Index: 1669600 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.8571. Min Act: -0.1700
Data Index: 7694715 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7946. Min Act: -0.1700
Data Index: 980931 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7633. Min Act: -0.1700
Data Index: 8812720 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7946. Min Act: -0.1700
Data Index: 1096329 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7007. Min Act: -0.1700
Data Index: 4549845 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7320. Min Act: -0.1700
Data Index: 996635 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7320. Min Act: -0.1700
Data Index: 6978050 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7320. Min Act: -0.1700
Data Index: 1096328 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7320. Min Act: -0.1700
Data Index: 2594030 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7007. Min Act: -0.1700
Data Index: 5888128 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7007. Min Act: -0.1700
Data Index: 4070292 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.7007. Min Act: -0.1700
Data Index: 4248352 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.6694. Min Act: -0.1700
Data Index: 6727047 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0447. Min Range: -4.0447
Max Act: 3.6694. Min Act: -0.1700
Data Index: 1603593 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19