Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1935 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.3886. Min Act: -0.1700
Data Index: 3605019 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.3729. Min Act: -0.1700
Data Index: 276486 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.3729. Min Act: -0.1700
Data Index: 1392841 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1845. Min Act: -0.1700
Data Index: 7910171 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1845. Min Act: -0.1700
Data Index: 4121819 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1845. Min Act: -0.1700
Data Index: 6690648 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1845. Min Act: -0.1700
Data Index: 6651203 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1688. Min Act: -0.1700
Data Index: 497933 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1688. Min Act: -0.1700
Data Index: 2070193 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1688. Min Act: -0.1700
Data Index: 3460690 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1530. Min Act: -0.1700
Data Index: 4090348 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1530. Min Act: -0.1700
Data Index: 6754702 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1688. Min Act: -0.1700
Data Index: 3110132 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1373. Min Act: -0.1700
Data Index: 5809682 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1373. Min Act: -0.1700
Data Index: 4232642 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1373. Min Act: -0.1700
Data Index: 3369080 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1373. Min Act: -0.1700
Data Index: 4534432 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1530. Min Act: -0.1700
Data Index: 5894458 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1373. Min Act: -0.1700
Data Index: 8695047 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3886. Min Range: -3.3886
Max Act: 3.1215. Min Act: -0.1700
Data Index: 2568511 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19