Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 111 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5783. Min Range: -8.5783
Max Act: 8.5783. Min Act: -0.1700
Data Index: 6312205 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5783. Min Range: -8.5783
Max Act: 8.5158. Min Act: -0.1700
Data Index: 2464871 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5783. Min Range: -8.5783
Max Act: 8.1408. Min Act: -0.1700
Data Index: 4464000 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5783. Min Range: -8.5783
Max Act: 8.0783. Min Act: -0.1700
Data Index: 780698 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.9533. Min Act: -0.1700
Data Index: 5835038 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.7658. Min Act: -0.1700
Data Index: 1239651 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.7658. Min Act: -0.1700
Data Index: 5390953 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.7033. Min Act: -0.1700
Data Index: 5924121 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.7033. Min Act: -0.1700
Data Index: 5107623 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.6096. Min Act: -0.1700
Data Index: 7763718 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.5783. Min Act: -0.1700
Data Index: 3860009 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.5471. Min Act: -0.1700
Data Index: 4089068 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.5471. Min Act: -0.1700
Data Index: 4324945 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.5471. Min Act: -0.1700
Data Index: 2719683 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.5783. Min Act: -0.1700
Data Index: 1505382 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.5783. Min Act: -0.1700
Data Index: 2458238 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.5158. Min Act: -0.1700
Data Index: 7203201 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.4846. Min Act: -0.1700
Data Index: 3047910 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.5471. Min Act: -0.1700
Data Index: 7591285 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5783. Min Range: -8.5783
Max Act: 7.4846. Min Act: -0.1700
Data Index: 1554261 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19