Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.6614. Min Act: -0.1700
Data Index: 6114185 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.4739. Min Act: -0.1700
Data Index: 572517 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.3489. Min Act: -0.1700
Data Index: 8440935 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.2864. Min Act: -0.1700
Data Index: 7856106 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.2239. Min Act: -0.1700
Data Index: 1098540 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.2239. Min Act: -0.1700
Data Index: 7199453 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.1614. Min Act: -0.1700
Data Index: 1396371 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.1926. Min Act: -0.1700
Data Index: 8236148 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.1614. Min Act: -0.1700
Data Index: 6811646 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.1614. Min Act: -0.1700
Data Index: 829352 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.0989. Min Act: -0.1700
Data Index: 4974230 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.0676. Min Act: -0.1700
Data Index: 3145813 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.0676. Min Act: -0.1700
Data Index: 5958901 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.0364. Min Act: -0.1700
Data Index: 1823447 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.0676. Min Act: -0.1700
Data Index: 7146389 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6614. Min Range: -7.6614
Max Act: 7.0051. Min Act: -0.1700
Data Index: 1263480 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6614. Min Range: -7.6614
Max Act: 6.9739. Min Act: -0.1700
Data Index: 2038555 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6614. Min Range: -7.6614
Max Act: 6.9739. Min Act: -0.1700
Data Index: 397657 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6614. Min Range: -7.6614
Max Act: 6.9426. Min Act: -0.1700
Data Index: 2729729 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6614. Min Range: -7.6614
Max Act: 6.9426. Min Act: -0.1700
Data Index: 1971090 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19