Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3047 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2182. Min Range: -7.2182
Max Act: 7.2182. Min Act: -0.1700
Data Index: 5201275 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2182. Min Range: -7.2182
Max Act: 7.1870. Min Act: -0.1700
Data Index: 2375975 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2182. Min Range: -7.2182
Max Act: 7.1557. Min Act: -0.1700
Data Index: 1745872 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2182. Min Range: -7.2182
Max Act: 7.0932. Min Act: -0.1700
Data Index: 3112936 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2182. Min Range: -7.2182
Max Act: 7.0620. Min Act: -0.1700
Data Index: 2089386 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2182. Min Range: -7.2182
Max Act: 7.0620. Min Act: -0.1700
Data Index: 8104916 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2182. Min Range: -7.2182
Max Act: 7.0307. Min Act: -0.1700
Data Index: 825003 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.9682. Min Act: -0.1700
Data Index: 3160124 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.9682. Min Act: -0.1700
Data Index: 3281115 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.9682. Min Act: -0.1700
Data Index: 1852837 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.9370. Min Act: -0.1700
Data Index: 7108828 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.8745. Min Act: -0.1700
Data Index: 1139141 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.8745. Min Act: -0.1700
Data Index: 5084602 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.8120. Min Act: -0.1700
Data Index: 3485064 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.7495. Min Act: -0.1700
Data Index: 7948407 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.7495. Min Act: -0.1700
Data Index: 498372 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.7182. Min Act: -0.1700
Data Index: 1899404 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.7182. Min Act: -0.1700
Data Index: 5824531 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.7182. Min Act: -0.1700
Data Index: 5900081 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2182. Min Range: -7.2182
Max Act: 6.6870. Min Act: -0.1700
Data Index: 5505257 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19