Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 490 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.6956. Min Act: -0.1700
Data Index: 8071897 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.6331. Min Act: -0.1700
Data Index: 6510685 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.5081. Min Act: -0.1700
Data Index: 1080459 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.5393. Min Act: -0.1700
Data Index: 56234 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.3831. Min Act: -0.1700
Data Index: 6028204 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.3206. Min Act: -0.1700
Data Index: 1820877 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.2893. Min Act: -0.1700
Data Index: 3310688 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.2893. Min Act: -0.1700
Data Index: 3418211 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.1956. Min Act: -0.1700
Data Index: 834194 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.1643. Min Act: -0.1700
Data Index: 1752809 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.1018. Min Act: -0.1700
Data Index: 3732292 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.0706. Min Act: -0.1700
Data Index: 6822756 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.0081. Min Act: -0.1700
Data Index: 741898 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.0393. Min Act: -0.1700
Data Index: 1863097 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.0081. Min Act: -0.1700
Data Index: 6237353 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.0081. Min Act: -0.1700
Data Index: 1861175 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.0081. Min Act: -0.1700
Data Index: 56236 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6956. Min Range: -6.6956
Max Act: 6.0081. Min Act: -0.1700
Data Index: 6498857 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6956. Min Range: -6.6956
Max Act: 5.9768. Min Act: -0.1700
Data Index: 1098971 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6956. Min Range: -6.6956
Max Act: 5.9768. Min Act: -0.1700
Data Index: 6121998 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19