Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.6658. Min Act: -0.1700
Data Index: 8134034 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.6033. Min Act: -0.1700
Data Index: 6338289 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.6033. Min Act: -0.1700
Data Index: 544647 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.5408. Min Act: -0.1700
Data Index: 2566718 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.5096. Min Act: -0.1700
Data Index: 2566717 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.4783. Min Act: -0.1700
Data Index: 87662 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.4158. Min Act: -0.1700
Data Index: 4952761 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.3846. Min Act: -0.1700
Data Index: 4023748 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.3846. Min Act: -0.1700
Data Index: 3422579 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.3846. Min Act: -0.1700
Data Index: 4180137 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.3533. Min Act: -0.1700
Data Index: 769321 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.3533. Min Act: -0.1700
Data Index: 5610313 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.3221. Min Act: -0.1700
Data Index: 782893 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.2908. Min Act: -0.1700
Data Index: 2793661 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.2908. Min Act: -0.1700
Data Index: 7593778 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.2908. Min Act: -0.1700
Data Index: 6492541 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.2908. Min Act: -0.1700
Data Index: 8037401 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.2908. Min Act: -0.1700
Data Index: 3957440 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.2908. Min Act: -0.1700
Data Index: 244608 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6658. Min Range: -5.6658
Max Act: 5.2596. Min Act: -0.1700
Data Index: 3625392 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19