Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4671 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4803. Min Range: -8.4803
Max Act: 8.4803. Min Act: -0.1700
Data Index: 5446103 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4803. Min Range: -8.4803
Max Act: 8.1053. Min Act: -0.1700
Data Index: 8195049 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4803. Min Range: -8.4803
Max Act: 8.1053. Min Act: -0.1700
Data Index: 2908140 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4803. Min Range: -8.4803
Max Act: 8.0428. Min Act: -0.1700
Data Index: 3714753 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.9491. Min Act: -0.1700
Data Index: 4810529 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.9491. Min Act: -0.1700
Data Index: 4717251 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.8866. Min Act: -0.1700
Data Index: 7342072 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.8866. Min Act: -0.1700
Data Index: 1567036 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.8553. Min Act: -0.1700
Data Index: 28491 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.7928. Min Act: -0.1700
Data Index: 4295706 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.7928. Min Act: -0.1700
Data Index: 6758545 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.7928. Min Act: -0.1700
Data Index: 3909524 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.7616. Min Act: -0.1700
Data Index: 2366853 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.7303. Min Act: -0.1700
Data Index: 2476908 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.7303. Min Act: -0.1700
Data Index: 634145 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.6366. Min Act: -0.1700
Data Index: 5033951 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.6053. Min Act: -0.1700
Data Index: 1867848 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.6366. Min Act: -0.1700
Data Index: 30136 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.6366. Min Act: -0.1700
Data Index: 4283895 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4803. Min Range: -8.4803
Max Act: 7.5428. Min Act: -0.1700
Data Index: 7040870 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19