Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1641 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1689. Min Range: -5.1689
Max Act: 5.1689. Min Act: -0.1700
Data Index: 3480826 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1689. Min Range: -5.1689
Max Act: 5.1064. Min Act: -0.1700
Data Index: 6926476 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1689. Min Range: -5.1689
Max Act: 5.0126. Min Act: -0.1700
Data Index: 1761804 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1689. Min Range: -5.1689
Max Act: 5.0126. Min Act: -0.1700
Data Index: 3979156 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1689. Min Range: -5.1689
Max Act: 5.0126. Min Act: -0.1700
Data Index: 2700136 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1689. Min Range: -5.1689
Max Act: 5.0126. Min Act: -0.1700
Data Index: 7755117 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.9814. Min Act: -0.1700
Data Index: 1528513 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.9501. Min Act: -0.1700
Data Index: 1825402 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.9501. Min Act: -0.1700
Data Index: 6621688 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.9501. Min Act: -0.1700
Data Index: 8786344 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.9189. Min Act: -0.1700
Data Index: 6621687 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.9189. Min Act: -0.1700
Data Index: 8726216 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.8876. Min Act: -0.1700
Data Index: 6621689 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.8876. Min Act: -0.1700
Data Index: 3730749 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.8876. Min Act: -0.1700
Data Index: 6066 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.9189. Min Act: -0.1700
Data Index: 8350603 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.8876. Min Act: -0.1700
Data Index: 8350602 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.8564. Min Act: -0.1700
Data Index: 5476294 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.8251. Min Act: -0.1700
Data Index: 5476296 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1689. Min Range: -5.1689
Max Act: 4.8251. Min Act: -0.1700
Data Index: 3480829 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19