Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 433 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1047. Min Range: -6.1047
Max Act: 6.1047. Min Act: -0.1700
Data Index: 7446221 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.9172. Min Act: -0.1700
Data Index: 2808832 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.8547. Min Act: -0.1700
Data Index: 6413384 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.8235. Min Act: -0.1700
Data Index: 8000011 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.7922. Min Act: -0.1700
Data Index: 5343746 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.7922. Min Act: -0.1700
Data Index: 8766815 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.7922. Min Act: -0.1700
Data Index: 7741122 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6985. Min Act: -0.1700
Data Index: 2816375 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.7297. Min Act: -0.1700
Data Index: 4593680 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6985. Min Act: -0.1700
Data Index: 6496711 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6985. Min Act: -0.1700
Data Index: 5305886 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6985. Min Act: -0.1700
Data Index: 5862182 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6985. Min Act: -0.1700
Data Index: 8591251 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6672. Min Act: -0.1700
Data Index: 8000004 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6360. Min Act: -0.1700
Data Index: 3049632 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6360. Min Act: -0.1700
Data Index: 7349090 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6360. Min Act: -0.1700
Data Index: 4598871 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6047. Min Act: -0.1700
Data Index: 456305 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6047. Min Act: -0.1700
Data Index: 2553 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1047. Min Range: -6.1047
Max Act: 5.6047. Min Act: -0.1700
Data Index: 4591581 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19