Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.6830. Min Act: -0.1700
Data Index: 2137414 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.6205. Min Act: -0.1700
Data Index: 1367868 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.4018. Min Act: -0.1700
Data Index: 7266679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.3080. Min Act: -0.1700
Data Index: 3238619 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.2768. Min Act: -0.1700
Data Index: 5165457 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.2455. Min Act: -0.1700
Data Index: 3562837 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.2455. Min Act: -0.1700
Data Index: 1041558 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.2143. Min Act: -0.1700
Data Index: 3589347 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.1830. Min Act: -0.1700
Data Index: 6714238 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.1518. Min Act: -0.1700
Data Index: 3509604 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.0580. Min Act: -0.1700
Data Index: 3547401 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6830. Min Range: -6.6830
Max Act: 6.0268. Min Act: -0.1700
Data Index: 2798004 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6830. Min Range: -6.6830
Max Act: 5.9955. Min Act: -0.1700
Data Index: 4082433 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6830. Min Range: -6.6830
Max Act: 5.9643. Min Act: -0.1700
Data Index: 5735806 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6830. Min Range: -6.6830
Max Act: 5.9955. Min Act: -0.1700
Data Index: 6108379 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6830. Min Range: -6.6830
Max Act: 5.9955. Min Act: -0.1700
Data Index: 3562840 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6830. Min Range: -6.6830
Max Act: 5.9643. Min Act: -0.1700
Data Index: 4923435 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6830. Min Range: -6.6830
Max Act: 5.9330. Min Act: -0.1700
Data Index: 7395857 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6830. Min Range: -6.6830
Max Act: 5.9018. Min Act: -0.1700
Data Index: 4117313 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6830. Min Range: -6.6830
Max Act: 5.8705. Min Act: -0.1700
Data Index: 5957545 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19