Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0609. Min Range: -4.0609
Max Act: 4.0609. Min Act: -0.1700
Data Index: 8157175 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.9671. Min Act: -0.1700
Data Index: 3094734 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.9045. Min Act: -0.1700
Data Index: 6507211 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.9045. Min Act: -0.1700
Data Index: 1504050 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.9045. Min Act: -0.1700
Data Index: 3825673 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.8420. Min Act: -0.1700
Data Index: 6993427 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.8107. Min Act: -0.1700
Data Index: 3594929 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7638. Min Act: -0.1700
Data Index: 4033703 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7638. Min Act: -0.1700
Data Index: 4995762 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7482. Min Act: -0.1700
Data Index: 579555 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7325. Min Act: -0.1700
Data Index: 284839 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7325. Min Act: -0.1700
Data Index: 4269129 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7169. Min Act: -0.1700
Data Index: 6247877 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7325. Min Act: -0.1700
Data Index: 5865832 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7169. Min Act: -0.1700
Data Index: 1492824 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7169. Min Act: -0.1700
Data Index: 6806360 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.7013. Min Act: -0.1700
Data Index: 3730185 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.6700. Min Act: -0.1700
Data Index: 5161982 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.6543. Min Act: -0.1700
Data Index: 8350662 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0609. Min Range: -4.0609
Max Act: 3.6543. Min Act: -0.1700
Data Index: 7243881 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19