Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 328 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0580. Min Range: -6.0580
Max Act: 6.0580. Min Act: -0.1700
Data Index: 3906422 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0580. Min Range: -6.0580
Max Act: 6.0268. Min Act: -0.1700
Data Index: 4690433 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.9955. Min Act: -0.1700
Data Index: 44391 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.9955. Min Act: -0.1700
Data Index: 7029921 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.9330. Min Act: -0.1700
Data Index: 1527164 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.8393. Min Act: -0.1700
Data Index: 5461154 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.8393. Min Act: -0.1700
Data Index: 4075911 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.8393. Min Act: -0.1700
Data Index: 2611194 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.8393. Min Act: -0.1700
Data Index: 6315084 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.7768. Min Act: -0.1700
Data Index: 1082068 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.7455. Min Act: -0.1700
Data Index: 3569528 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.6830. Min Act: -0.1700
Data Index: 2021584 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.6830. Min Act: -0.1700
Data Index: 525049 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.6518. Min Act: -0.1700
Data Index: 1261570 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.6205. Min Act: -0.1700
Data Index: 2408662 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.6205. Min Act: -0.1700
Data Index: 5627493 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.6205. Min Act: -0.1700
Data Index: 7883756 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.5893. Min Act: -0.1700
Data Index: 3639701 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.5580. Min Act: -0.1700
Data Index: 7430908 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0580. Min Range: -6.0580
Max Act: 5.5893. Min Act: -0.1700
Data Index: 7011695 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19