Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4195 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.9855. Min Act: -0.1700
Data Index: 4056668 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.9855. Min Act: -0.1700
Data Index: 7349197 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.9542. Min Act: -0.1700
Data Index: 4049629 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.9542. Min Act: -0.1700
Data Index: 4444526 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.9230. Min Act: -0.1700
Data Index: 1349307 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.9230. Min Act: -0.1700
Data Index: 640983 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.9230. Min Act: -0.1700
Data Index: 7064198 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.8917. Min Act: -0.1700
Data Index: 7205533 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.8917. Min Act: -0.1700
Data Index: 6651111 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.8917. Min Act: -0.1700
Data Index: 819165 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.8605. Min Act: -0.1700
Data Index: 7641312 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.8605. Min Act: -0.1700
Data Index: 4254377 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.8292. Min Act: -0.1700
Data Index: 4386307 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.7980. Min Act: -0.1700
Data Index: 8588625 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.7980. Min Act: -0.1700
Data Index: 8198416 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.7667. Min Act: -0.1700
Data Index: 2241417 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.7667. Min Act: -0.1700
Data Index: 2638675 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.7355. Min Act: -0.1700
Data Index: 3669077 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.5792. Min Act: -0.1700
Data Index: 1847927 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9855. Min Range: -6.9855
Max Act: 6.4855. Min Act: -0.1700
Data Index: 4971131 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19