Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5089. Min Range: -10.5089
Max Act: 10.5089. Min Act: -0.1700
Data Index: 3432769 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.9464. Min Act: -0.1700
Data Index: 2311695 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.9464. Min Act: -0.1700
Data Index: 1121423 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.6964. Min Act: -0.1700
Data Index: 3047607 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3839. Min Act: -0.1700
Data Index: 4097657 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.4464. Min Act: -0.1700
Data Index: 7342663 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.4464. Min Act: -0.1700
Data Index: 5421823 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3839. Min Act: -0.1700
Data Index: 4300585 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3839. Min Act: -0.1700
Data Index: 303183 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3839. Min Act: -0.1700
Data Index: 7708284 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3214. Min Act: -0.1700
Data Index: 591833 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3214. Min Act: -0.1700
Data Index: 916287 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3214. Min Act: -0.1700
Data Index: 8460987 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3839. Min Act: -0.1700
Data Index: 4356098 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.2589. Min Act: -0.1700
Data Index: 7635462 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.3214. Min Act: -0.1700
Data Index: 44470 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.1964. Min Act: -0.1700
Data Index: 7625489 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.2589. Min Act: -0.1700
Data Index: 6685041 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.2589. Min Act: -0.1700
Data Index: 3711931 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5089. Min Range: -10.5089
Max Act: 9.2589. Min Act: -0.1700
Data Index: 60934 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19