Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4379 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1739. Min Range: -3.1739
Max Act: 3.1739. Min Act: -0.1700
Data Index: 8487692 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1739. Min Range: -3.1739
Max Act: 3.0005. Min Act: -0.1700
Data Index: 5239914 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.9847. Min Act: -0.1700
Data Index: 8793193 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.9214. Min Act: -0.1700
Data Index: 6835934 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.9372. Min Act: -0.1700
Data Index: 6170957 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.9214. Min Act: -0.1700
Data Index: 4252264 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.9214. Min Act: -0.1700
Data Index: 1761833 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.9055. Min Act: -0.1700
Data Index: 2817115 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.8897. Min Act: -0.1700
Data Index: 5283046 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.8579. Min Act: -0.1700
Data Index: 7594176 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.8261. Min Act: -0.1700
Data Index: 2000998 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.8102. Min Act: -0.1700
Data Index: 2261886 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.8102. Min Act: -0.1700
Data Index: 4494863 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.7943. Min Act: -0.1700
Data Index: 6462718 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.7943. Min Act: -0.1700
Data Index: 2361333 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.7943. Min Act: -0.1700
Data Index: 1625743 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.7943. Min Act: -0.1700
Data Index: 934013 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.7783. Min Act: -0.1700
Data Index: 5922029 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.7943. Min Act: -0.1700
Data Index: 6670328 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1739. Min Range: -3.1739
Max Act: 2.7783. Min Act: -0.1700
Data Index: 3807369 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19