Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5084 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5934. Min Range: -9.5934
Max Act: 9.5934. Min Act: -0.1700
Data Index: 7678494 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5934. Min Range: -9.5934
Max Act: 9.2809. Min Act: -0.1700
Data Index: 2167961 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5934. Min Range: -9.5934
Max Act: 9.0934. Min Act: -0.1700
Data Index: 738291 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.9684. Min Act: -0.1700
Data Index: 2268389 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.9684. Min Act: -0.1700
Data Index: 1397288 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.9059. Min Act: -0.1700
Data Index: 3752240 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.9059. Min Act: -0.1700
Data Index: 4955604 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 4323063 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 2774609 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 875047 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 818857 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.8434. Min Act: -0.1700
Data Index: 8493911 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.7184. Min Act: -0.1700
Data Index: 7503846 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.7809. Min Act: -0.1700
Data Index: 7495949 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.7809. Min Act: -0.1700
Data Index: 867119 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.7809. Min Act: -0.1700
Data Index: 147543 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.7809. Min Act: -0.1700
Data Index: 8458144 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.7809. Min Act: -0.1700
Data Index: 6281524 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.7184. Min Act: -0.1700
Data Index: 5740417 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5934. Min Range: -9.5934
Max Act: 8.7184. Min Act: -0.1700
Data Index: 5117758 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19