Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6278. Min Range: -9.6278
Max Act: 9.6278. Min Act: -0.1700
Data Index: 8665425 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.8778. Min Act: -0.1700
Data Index: 7635362 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.9403. Min Act: -0.1700
Data Index: 4878496 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.6278. Min Act: -0.1700
Data Index: 2406913 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.7528. Min Act: -0.1700
Data Index: 2723839 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.5653. Min Act: -0.1700
Data Index: 5569750 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.5028. Min Act: -0.1700
Data Index: 8449734 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.5028. Min Act: -0.1700
Data Index: 4597670 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.3778. Min Act: -0.1700
Data Index: 5490789 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.3778. Min Act: -0.1698
Data Index: 1277311 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.3153. Min Act: -0.1700
Data Index: 6895552 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.3153. Min Act: -0.1700
Data Index: 5020785 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.3153. Min Act: -0.1700
Data Index: 8449735 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.2528. Min Act: -0.1700
Data Index: 6229677 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.2528. Min Act: -0.1700
Data Index: 4542498 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.1903. Min Act: -0.1700
Data Index: 1092323 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.1903. Min Act: -0.1700
Data Index: 4316432 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.2528. Min Act: -0.1700
Data Index: 1403713 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.1903. Min Act: -0.1700
Data Index: 8780835 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6278. Min Range: -9.6278
Max Act: 8.0965. Min Act: -0.1700
Data Index: 1277307 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19