Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2840 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3866. Min Range: -8.3866
Max Act: 8.3866. Min Act: -0.1700
Data Index: 1023258 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3866. Min Range: -8.3866
Max Act: 8.3866. Min Act: -0.1700
Data Index: 4912768 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3866. Min Range: -8.3866
Max Act: 8.1366. Min Act: -0.1700
Data Index: 6650254 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3866. Min Range: -8.3866
Max Act: 8.1366. Min Act: -0.1700
Data Index: 1693172 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.9491. Min Act: -0.1700
Data Index: 8067400 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.9491. Min Act: -0.1700
Data Index: 2484168 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.8553. Min Act: -0.1700
Data Index: 3964624 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.8241. Min Act: -0.1700
Data Index: 3695327 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.8241. Min Act: -0.1700
Data Index: 7494508 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.7303. Min Act: -0.1700
Data Index: 5982124 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.7303. Min Act: -0.1700
Data Index: 3987577 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.6991. Min Act: -0.1700
Data Index: 8553565 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.6053. Min Act: -0.1700
Data Index: 2428169 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.6053. Min Act: -0.1700
Data Index: 3943866 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.6053. Min Act: -0.1700
Data Index: 3710709 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.6366. Min Act: -0.1700
Data Index: 2109881 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.5741. Min Act: -0.1700
Data Index: 7856785 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.5741. Min Act: -0.1700
Data Index: 7429966 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.5428. Min Act: -0.1700
Data Index: 7042889 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3866. Min Range: -8.3866
Max Act: 7.5116. Min Act: -0.1700
Data Index: 4390214 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19