Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 895 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2625. Min Range: -7.2625
Max Act: 7.2625. Min Act: -0.1700
Data Index: 403483 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2625. Min Range: -7.2625
Max Act: 7.0750. Min Act: -0.1700
Data Index: 5563647 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.9500. Min Act: -0.1700
Data Index: 4118182 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.8562. Min Act: -0.1700
Data Index: 4149176 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.8250. Min Act: -0.1700
Data Index: 6462126 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.8250. Min Act: -0.1700
Data Index: 8565421 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.7937. Min Act: -0.1700
Data Index: 3091297 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.5750. Min Act: -0.1700
Data Index: 2224273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.5750. Min Act: -0.1700
Data Index: 5050381 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.5750. Min Act: -0.1700
Data Index: 271938 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.5750. Min Act: -0.1700
Data Index: 1859416 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.5437. Min Act: -0.1700
Data Index: 4363522 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.5125. Min Act: -0.1700
Data Index: 2066507 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.5125. Min Act: -0.1700
Data Index: 4385110 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.4812. Min Act: -0.1700
Data Index: 5798395 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.4500. Min Act: -0.1700
Data Index: 2916513 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.4500. Min Act: -0.1700
Data Index: 5385250 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.4500. Min Act: -0.1700
Data Index: 4468790 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.4500. Min Act: -0.1700
Data Index: 7948343 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2625. Min Range: -7.2625
Max Act: 6.4500. Min Act: -0.1700
Data Index: 1496530 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19