Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.3730. Min Act: -0.1700
Data Index: 8139364 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.1855. Min Act: -0.1700
Data Index: 2063675 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.1542. Min Act: -0.1700
Data Index: 269092 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.1542. Min Act: -0.1700
Data Index: 6163722 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.1230. Min Act: -0.1700
Data Index: 941160 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.1230. Min Act: -0.1700
Data Index: 4295676 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.0917. Min Act: -0.1700
Data Index: 8682766 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.0917. Min Act: -0.1700
Data Index: 5643869 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.0917. Min Act: -0.1700
Data Index: 2109583 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.0605. Min Act: -0.1700
Data Index: 2188515 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.0917. Min Act: -0.1700
Data Index: 7348141 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3730. Min Range: -5.3730
Max Act: 4.9980. Min Act: -0.1700
Data Index: 7721505 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.0292. Min Act: -0.1700
Data Index: 3293669 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3730. Min Range: -5.3730
Max Act: 4.9980. Min Act: -0.1700
Data Index: 39650 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3730. Min Range: -5.3730
Max Act: 5.0292. Min Act: -0.1700
Data Index: 166975 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3730. Min Range: -5.3730
Max Act: 4.9667. Min Act: -0.1700
Data Index: 298921 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3730. Min Range: -5.3730
Max Act: 4.9042. Min Act: -0.1700
Data Index: 7542331 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3730. Min Range: -5.3730
Max Act: 4.9355. Min Act: -0.1700
Data Index: 6760882 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3730. Min Range: -5.3730
Max Act: 4.9042. Min Act: -0.1700
Data Index: 3091080 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3730. Min Range: -5.3730
Max Act: 4.9042. Min Act: -0.1700
Data Index: 8576962 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19