Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.8528. Min Act: -0.1700
Data Index: 8039376 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.8528. Min Act: -0.1700
Data Index: 5335390 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.7903. Min Act: -0.1700
Data Index: 8207008 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.7903. Min Act: -0.1700
Data Index: 2927630 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6653. Min Act: -0.1700
Data Index: 4183572 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6028. Min Act: -0.1700
Data Index: 1105004 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6653. Min Act: -0.1700
Data Index: 8491544 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6653. Min Act: -0.1700
Data Index: 8614589 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6028. Min Act: -0.1700
Data Index: 4225156 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6653. Min Act: -0.1700
Data Index: 6737088 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6028. Min Act: -0.1700
Data Index: 6554687 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6028. Min Act: -0.1700
Data Index: 6487753 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6028. Min Act: -0.1700
Data Index: 2977037 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.6028. Min Act: -0.1700
Data Index: 1817292 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.5403. Min Act: -0.1700
Data Index: 1344228 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.4778. Min Act: -0.1700
Data Index: 5771708 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.5403. Min Act: -0.1700
Data Index: 5863833 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.5403. Min Act: -0.1700
Data Index: 6123931 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.5403. Min Act: -0.1700
Data Index: 1915896 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8528. Min Range: -8.8528
Max Act: 8.5403. Min Act: -0.1700
Data Index: 6803503 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19