Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1288 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3997. Min Range: -8.3997
Max Act: 8.3997. Min Act: -0.1700
Data Index: 3640882 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.9935. Min Act: -0.1700
Data Index: 8708894 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.9935. Min Act: -0.1700
Data Index: 6942135 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.8685. Min Act: -0.1700
Data Index: 3319655 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.8060. Min Act: -0.1700
Data Index: 4737964 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.7435. Min Act: -0.1700
Data Index: 5879328 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.7122. Min Act: -0.1700
Data Index: 3084095 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.6810. Min Act: -0.1700
Data Index: 551692 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.6810. Min Act: -0.1700
Data Index: 1762572 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.6497. Min Act: -0.1700
Data Index: 1179250 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.6185. Min Act: -0.1700
Data Index: 3160695 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.6497. Min Act: -0.1700
Data Index: 752709 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.6497. Min Act: -0.1700
Data Index: 4195274 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.6185. Min Act: -0.1700
Data Index: 3005192 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.5872. Min Act: -0.1700
Data Index: 3406021 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.5560. Min Act: -0.1700
Data Index: 6624057 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.4935. Min Act: -0.1700
Data Index: 4678432 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.4935. Min Act: -0.1700
Data Index: 8204827 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.4622. Min Act: -0.1700
Data Index: 1635923 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3997. Min Range: -8.3997
Max Act: 7.3997. Min Act: -0.1700
Data Index: 2614743 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19