Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5793 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.5174. Min Act: -0.1700
Data Index: 5055781 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.3137. Min Act: -0.1700
Data Index: 6973782 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.2980. Min Act: -0.1700
Data Index: 8031660 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.2823. Min Act: -0.1700
Data Index: 1741082 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.2666. Min Act: -0.1700
Data Index: 1674494 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.2666. Min Act: -0.1700
Data Index: 5086480 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.2194. Min Act: -0.1700
Data Index: 8290472 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.2194. Min Act: -0.1700
Data Index: 3543649 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.2037. Min Act: -0.1700
Data Index: 6808186 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1880. Min Act: -0.1700
Data Index: 8686089 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1880. Min Act: -0.1700
Data Index: 3348336 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1722. Min Act: -0.1700
Data Index: 1465037 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1722. Min Act: -0.1700
Data Index: 1728412 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1565. Min Act: -0.1700
Data Index: 4073049 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1407. Min Act: -0.1700
Data Index: 4918923 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1250. Min Act: -0.1700
Data Index: 5734749 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1250. Min Act: -0.1700
Data Index: 6737590 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.1092. Min Act: -0.1700
Data Index: 2068441 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.0935. Min Act: -0.1700
Data Index: 1337695 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5174. Min Range: -3.5174
Max Act: 3.0935. Min Act: -0.1700
Data Index: 479369 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19