Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3844 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1570. Min Range: -5.1570
Max Act: 5.1570. Min Act: -0.1700
Data Index: 4318261 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1570. Min Range: -5.1570
Max Act: 5.1258. Min Act: -0.1700
Data Index: 5553647 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1570. Min Range: -5.1570
Max Act: 5.1258. Min Act: -0.1700
Data Index: 3931619 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1570. Min Range: -5.1570
Max Act: 5.1570. Min Act: -0.1699
Data Index: 8561733 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1570. Min Range: -5.1570
Max Act: 5.0633. Min Act: -0.1700
Data Index: 326124 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1570. Min Range: -5.1570
Max Act: 5.0320. Min Act: -0.1700
Data Index: 3006685 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1570. Min Range: -5.1570
Max Act: 5.0320. Min Act: -0.1700
Data Index: 1329773 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9695. Min Act: -0.1700
Data Index: 760148 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9695. Min Act: -0.1700
Data Index: 5556386 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9070. Min Act: -0.1700
Data Index: 283415 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9383. Min Act: -0.1700
Data Index: 954116 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9070. Min Act: -0.1700
Data Index: 4398620 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9070. Min Act: -0.1699
Data Index: 7480162 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9070. Min Act: -0.1700
Data Index: 2890495 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9383. Min Act: -0.1700
Data Index: 1908579 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9070. Min Act: -0.1700
Data Index: 824404 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9070. Min Act: -0.1700
Data Index: 8429819 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.8758. Min Act: -0.1700
Data Index: 1727150 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9070. Min Act: -0.1697
Data Index: 3704918 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1570. Min Range: -5.1570
Max Act: 4.9070. Min Act: -0.1700
Data Index: 7961917 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19