Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.4697. Min Act: -0.1700
Data Index: 105594 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.4072. Min Act: -0.1700
Data Index: 3709886 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.4072. Min Act: -0.1700
Data Index: 405927 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.3760. Min Act: -0.1700
Data Index: 3080185 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.2822. Min Act: -0.1700
Data Index: 8462524 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.2822. Min Act: -0.1700
Data Index: 1376239 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.2197. Min Act: -0.1700
Data Index: 573724 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.2510. Min Act: -0.1700
Data Index: 6590237 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.2510. Min Act: -0.1700
Data Index: 8347658 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.2197. Min Act: -0.1700
Data Index: 405928 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.2197. Min Act: -0.1700
Data Index: 1861106 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1885. Min Act: -0.1700
Data Index: 5191405 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1885. Min Act: -0.1700
Data Index: 6392935 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1885. Min Act: -0.1700
Data Index: 6542581 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1259. Min Act: -0.1700
Data Index: 6498151 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1572. Min Act: -0.1700
Data Index: 2097925 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1259. Min Act: -0.1700
Data Index: 8066235 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1259. Min Act: -0.1700
Data Index: 8187725 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1259. Min Act: -0.1700
Data Index: 8309553 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4697. Min Range: -4.4697
Max Act: 4.1259. Min Act: -0.1700
Data Index: 8309552 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19