Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3721 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2713. Min Range: -6.2713
Max Act: 6.2713. Min Act: -0.1700
Data Index: 5272674 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2713. Min Range: -6.2713
Max Act: 6.1150. Min Act: -0.1700
Data Index: 7478835 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9900. Min Act: -0.1700
Data Index: 7060607 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9900. Min Act: -0.1700
Data Index: 2965017 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9588. Min Act: -0.1700
Data Index: 4258181 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9275. Min Act: -0.1699
Data Index: 4313334 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9588. Min Act: -0.1700
Data Index: 8766954 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9275. Min Act: -0.1700
Data Index: 3713188 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9275. Min Act: -0.1700
Data Index: 6841838 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9275. Min Act: -0.1700
Data Index: 3658251 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9275. Min Act: -0.1700
Data Index: 8766955 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9275. Min Act: -0.1700
Data Index: 5055254 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.9275. Min Act: -0.1700
Data Index: 733371 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.8963. Min Act: -0.1700
Data Index: 4790437 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.8963. Min Act: -0.1700
Data Index: 5255111 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.8650. Min Act: -0.1700
Data Index: 1677493 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.8338. Min Act: -0.1700
Data Index: 2756364 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.8338. Min Act: -0.1700
Data Index: 7740477 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.8338. Min Act: -0.1700
Data Index: 3382102 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2713. Min Range: -6.2713
Max Act: 5.8025. Min Act: -0.1700
Data Index: 5340643 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19