Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5078 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0697. Min Range: -6.0697
Max Act: 6.0697. Min Act: -0.1700
Data Index: 3424115 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.8510. Min Act: -0.1700
Data Index: 8477186 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.7572. Min Act: -0.1700
Data Index: 8477185 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.7260. Min Act: -0.1700
Data Index: 4511040 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.6635. Min Act: -0.1700
Data Index: 6611990 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.6635. Min Act: -0.1700
Data Index: 8805482 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.6635. Min Act: -0.1700
Data Index: 6093150 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.6322. Min Act: -0.1700
Data Index: 8526815 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5697. Min Act: -0.1700
Data Index: 4085174 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5697. Min Act: -0.1700
Data Index: 2427751 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5385. Min Act: -0.1700
Data Index: 2577150 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5385. Min Act: -0.1700
Data Index: 4952447 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5385. Min Act: -0.1700
Data Index: 6208760 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5385. Min Act: -0.1700
Data Index: 6557199 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5385. Min Act: -0.1700
Data Index: 3258721 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5385. Min Act: -0.1700
Data Index: 7487922 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5072. Min Act: -0.1700
Data Index: 3161520 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5072. Min Act: -0.1700
Data Index: 2365049 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.5072. Min Act: -0.1700
Data Index: 3204153 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0697. Min Range: -6.0697
Max Act: 5.4760. Min Act: -0.1700
Data Index: 175193 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19