Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1300 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.6051. Min Act: -0.1700
Data Index: 5762666 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.5738. Min Act: -0.1700
Data Index: 5762664 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.3551. Min Act: -0.1700
Data Index: 7809200 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.3551. Min Act: -0.1700
Data Index: 5069745 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.3238. Min Act: -0.1700
Data Index: 844563 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.2926. Min Act: -0.1700
Data Index: 3478188 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.2926. Min Act: -0.1700
Data Index: 7122954 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.2613. Min Act: -0.1700
Data Index: 844561 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.2301. Min Act: -0.1700
Data Index: 2265781 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1988. Min Act: -0.1700
Data Index: 57627 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1988. Min Act: -0.1700
Data Index: 5126331 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1988. Min Act: -0.1700
Data Index: 5139035 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1988. Min Act: -0.1700
Data Index: 2895301 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1988. Min Act: -0.1700
Data Index: 8603358 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1988. Min Act: -0.1700
Data Index: 6964967 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1676. Min Act: -0.1700
Data Index: 1989682 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1988. Min Act: -0.1700
Data Index: 1893645 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1676. Min Act: -0.1700
Data Index: 4927533 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1676. Min Act: -0.1700
Data Index: 3444311 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6051. Min Range: -5.6051
Max Act: 5.1676. Min Act: -0.1700
Data Index: 7017076 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19