Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5879 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3845. Min Act: -0.1700
Data Index: 7785155 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3689. Min Act: -0.1700
Data Index: 705867 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3532. Min Act: -0.1700
Data Index: 8492739 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3375. Min Act: -0.1700
Data Index: 5511720 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3375. Min Act: -0.1700
Data Index: 1434331 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3218. Min Act: -0.1700
Data Index: 4273514 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3218. Min Act: -0.1700
Data Index: 441650 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3218. Min Act: -0.1700
Data Index: 462242 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3061. Min Act: -0.1700
Data Index: 130227 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3061. Min Act: -0.1700
Data Index: 262793 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3061. Min Act: -0.1700
Data Index: 8685320 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3218. Min Act: -0.1700
Data Index: 8014358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3061. Min Act: -0.1700
Data Index: 5725776 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3061. Min Act: -0.1700
Data Index: 3223828 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.3061. Min Act: -0.1700
Data Index: 4459722 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.2904. Min Act: -0.1700
Data Index: 5596596 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.2904. Min Act: -0.1700
Data Index: 353531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.2904. Min Act: -0.1700
Data Index: 2255516 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.2904. Min Act: -0.1700
Data Index: 2169833 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3845. Min Range: -3.3845
Max Act: 3.2904. Min Act: -0.1700
Data Index: 4281330 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19