Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5472 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.4381. Min Act: -0.1700
Data Index: 4034440 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.3444. Min Act: -0.1700
Data Index: 841646 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.3444. Min Act: -0.1700
Data Index: 3493761 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.3131. Min Act: -0.1700
Data Index: 7293247 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.3444. Min Act: -0.1700
Data Index: 6557686 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.2819. Min Act: -0.1700
Data Index: 4638195 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1881. Min Act: -0.1700
Data Index: 5127478 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1881. Min Act: -0.1700
Data Index: 5769224 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1881. Min Act: -0.1700
Data Index: 279986 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1569. Min Act: -0.1700
Data Index: 582036 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1881. Min Act: -0.1700
Data Index: 7318731 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1881. Min Act: -0.1700
Data Index: 4056703 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1569. Min Act: -0.1700
Data Index: 7099341 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1569. Min Act: -0.1700
Data Index: 2297698 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1569. Min Act: -0.1700
Data Index: 3228835 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1881. Min Act: -0.1700
Data Index: 8085293 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1569. Min Act: -0.1700
Data Index: 177455 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1256. Min Act: -0.1700
Data Index: 7554055 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1256. Min Act: -0.1700
Data Index: 7940982 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4381. Min Range: -6.4381
Max Act: 6.1569. Min Act: -0.1700
Data Index: 5629769 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19