Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5817 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5958. Min Act: -0.1700
Data Index: 4923427 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5645. Min Act: -0.1700
Data Index: 4719672 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5333. Min Act: -0.1700
Data Index: 5734255 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5333. Min Act: -0.1700
Data Index: 3947987 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5333. Min Act: -0.1700
Data Index: 8741037 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5333. Min Act: -0.1700
Data Index: 8001713 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5333. Min Act: -0.1700
Data Index: 701701 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.5020. Min Act: -0.1700
Data Index: 2639197 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4708. Min Act: -0.1700
Data Index: 1963004 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4708. Min Act: -0.1700
Data Index: 8199667 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4708. Min Act: -0.1700
Data Index: 2521748 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4708. Min Act: -0.1700
Data Index: 8751969 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4395. Min Act: -0.1700
Data Index: 4586304 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4395. Min Act: -0.1700
Data Index: 6483751 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.4083. Min Act: -0.1700
Data Index: 5163819 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3145. Min Act: -0.1700
Data Index: 7616630 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3770. Min Act: -0.1700
Data Index: 7296075 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 3802286 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.2833. Min Act: -0.1700
Data Index: 5047541 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5958. Min Range: -4.5958
Max Act: 4.3145. Min Act: -0.1700
Data Index: 7434223 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19