Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.4768. Min Act: -0.1700
Data Index: 8407165 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.4143. Min Act: -0.1700
Data Index: 6626596 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.1956. Min Act: -0.1700
Data Index: 1772592 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.1643. Min Act: -0.1700
Data Index: 8699583 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.1643. Min Act: -0.1700
Data Index: 4472259 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.1018. Min Act: -0.1700
Data Index: 2130789 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.1018. Min Act: -0.1700
Data Index: 4226333 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0706. Min Act: -0.1700
Data Index: 4475969 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.1018. Min Act: -0.1700
Data Index: 7649333 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0706. Min Act: -0.1700
Data Index: 4619395 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0706. Min Act: -0.1700
Data Index: 7784839 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0393. Min Act: -0.1700
Data Index: 7695625 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0393. Min Act: -0.1700
Data Index: 529262 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0393. Min Act: -0.1700
Data Index: 5353462 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0393. Min Act: -0.1700
Data Index: 1580089 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0393. Min Act: -0.1700
Data Index: 1480420 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0081. Min Act: -0.1700
Data Index: 7863922 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0081. Min Act: -0.1700
Data Index: 134500 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4768. Min Range: -5.4768
Max Act: 5.0081. Min Act: -0.1700
Data Index: 1801530 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4768. Min Range: -5.4768
Max Act: 4.9768. Min Act: -0.1700
Data Index: 8247540 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19