Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4443. Min Range: -6.4443
Max Act: 6.4443. Min Act: -0.1700
Data Index: 2083530 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4443. Min Range: -6.4443
Max Act: 6.1006. Min Act: -0.1700
Data Index: 2736643 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4443. Min Range: -6.4443
Max Act: 6.0693. Min Act: -0.1700
Data Index: 8012558 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4443. Min Range: -6.4443
Max Act: 6.0068. Min Act: -0.1700
Data Index: 3651271 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.9443. Min Act: -0.1700
Data Index: 2450404 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.9443. Min Act: -0.1700
Data Index: 1935516 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.9443. Min Act: -0.1700
Data Index: 5163679 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.9443. Min Act: -0.1700
Data Index: 5379252 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.9131. Min Act: -0.1700
Data Index: 2677221 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.9131. Min Act: -0.1700
Data Index: 6302550 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.9131. Min Act: -0.1700
Data Index: 2511211 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8818. Min Act: -0.1700
Data Index: 8104507 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8506. Min Act: -0.1700
Data Index: 4507522 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8506. Min Act: -0.1700
Data Index: 8145253 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8506. Min Act: -0.1700
Data Index: 3226177 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8193. Min Act: -0.1700
Data Index: 6729307 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8193. Min Act: -0.1700
Data Index: 7260066 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8506. Min Act: -0.1700
Data Index: 8772825 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8818. Min Act: -0.1700
Data Index: 3899774 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4443. Min Range: -6.4443
Max Act: 5.8506. Min Act: -0.1700
Data Index: 1506427 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19