Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.4744. Min Act: -0.1700
Data Index: 6598864 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.3807. Min Act: -0.1700
Data Index: 3048139 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.3494. Min Act: -0.1700
Data Index: 1556131 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.2869. Min Act: -0.1700
Data Index: 5208904 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.1307. Min Act: -0.1700
Data Index: 771321 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.1307. Min Act: -0.1700
Data Index: 8157932 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.0682. Min Act: -0.1700
Data Index: 8035850 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.0369. Min Act: -0.1700
Data Index: 5561365 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.0369. Min Act: -0.1700
Data Index: 7542748 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4744. Min Range: -7.4744
Max Act: 7.0057. Min Act: -0.1700
Data Index: 3644521 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.9744. Min Act: -0.1700
Data Index: 6731513 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.9432. Min Act: -0.1700
Data Index: 2506586 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.9432. Min Act: -0.1700
Data Index: 2703952 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.9432. Min Act: -0.1700
Data Index: 2222790 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.9119. Min Act: -0.1700
Data Index: 4200773 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.9432. Min Act: -0.1700
Data Index: 835633 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.8807. Min Act: -0.1700
Data Index: 5014416 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.8494. Min Act: -0.1700
Data Index: 5653008 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.8807. Min Act: -0.1700
Data Index: 4083624 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4744. Min Range: -7.4744
Max Act: 6.8807. Min Act: -0.1700
Data Index: 6093775 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19