Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4229. Min Range: -10.4229
Max Act: 10.4229. Min Act: -0.1700
Data Index: 2612184 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4229. Min Range: -10.4229
Max Act: 10.2979. Min Act: -0.1700
Data Index: 3201132 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4229. Min Range: -10.4229
Max Act: 10.2354. Min Act: -0.1700
Data Index: 8564977 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4229. Min Range: -10.4229
Max Act: 10.1729. Min Act: -0.1700
Data Index: 5925495 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.8604. Min Act: -0.1700
Data Index: 3930882 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7979. Min Act: -0.1700
Data Index: 2016748 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7979. Min Act: -0.1700
Data Index: 7907633 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7979. Min Act: -0.1700
Data Index: 3385849 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7979. Min Act: -0.1700
Data Index: 7580641 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7354. Min Act: -0.1700
Data Index: 4111196 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7354. Min Act: -0.1700
Data Index: 7799975 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7354. Min Act: -0.1700
Data Index: 4787134 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7354. Min Act: -0.1700
Data Index: 8467317 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.7354. Min Act: -0.1700
Data Index: 2086408 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.6729. Min Act: -0.1700
Data Index: 8545431 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.6729. Min Act: -0.1700
Data Index: 5625055 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.6729. Min Act: -0.1700
Data Index: 844769 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.6104. Min Act: -0.1700
Data Index: 6629339 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.6104. Min Act: -0.1700
Data Index: 4725394 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4229. Min Range: -10.4229
Max Act: 9.6104. Min Act: -0.1700
Data Index: 6275514 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19