Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 319 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.5976. Min Act: -0.1700
Data Index: 56155 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.4726. Min Act: -0.1700
Data Index: 5761936 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.3476. Min Act: -0.1700
Data Index: 2332156 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.2226. Min Act: -0.1700
Data Index: 4377280 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.1601. Min Act: -0.1700
Data Index: 4578552 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.1288. Min Act: -0.1700
Data Index: 4565866 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.1288. Min Act: -0.1700
Data Index: 3788538 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.0976. Min Act: -0.1700
Data Index: 546086 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.0351. Min Act: -0.1700
Data Index: 3084176 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.0038. Min Act: -0.1700
Data Index: 7931850 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.0038. Min Act: -0.1700
Data Index: 1050718 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.0038. Min Act: -0.1700
Data Index: 2958588 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5976. Min Range: -6.5976
Max Act: 6.0038. Min Act: -0.1700
Data Index: 3268671 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5976. Min Range: -6.5976
Max Act: 5.9413. Min Act: -0.1700
Data Index: 4403780 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5976. Min Range: -6.5976
Max Act: 5.9101. Min Act: -0.1700
Data Index: 5618507 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5976. Min Range: -6.5976
Max Act: 5.9101. Min Act: -0.1700
Data Index: 5201239 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5976. Min Range: -6.5976
Max Act: 5.8788. Min Act: -0.1700
Data Index: 6969630 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5976. Min Range: -6.5976
Max Act: 5.8788. Min Act: -0.1700
Data Index: 413066 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5976. Min Range: -6.5976
Max Act: 5.8788. Min Act: -0.1700
Data Index: 4785593 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5976. Min Range: -6.5976
Max Act: 5.8788. Min Act: -0.1700
Data Index: 2256447 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19