Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.9091. Min Act: -0.1700
Data Index: 2253266 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.9091. Min Act: -0.1700
Data Index: 3336043 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.7841. Min Act: -0.1700
Data Index: 2337408 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.7529. Min Act: -0.1700
Data Index: 5492283 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.6591. Min Act: -0.1700
Data Index: 3646817 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.5966. Min Act: -0.1700
Data Index: 3091574 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.5966. Min Act: -0.1700
Data Index: 5420628 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.5966. Min Act: -0.1700
Data Index: 290156 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.5341. Min Act: -0.1700
Data Index: 6031239 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.5029. Min Act: -0.1700
Data Index: 1840104 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.5029. Min Act: -0.1700
Data Index: 5115497 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.4716. Min Act: -0.1700
Data Index: 202518 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.4716. Min Act: -0.1700
Data Index: 465602 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.4404. Min Act: -0.1700
Data Index: 8457020 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.4404. Min Act: -0.1700
Data Index: 7275269 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.4404. Min Act: -0.1700
Data Index: 5824986 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.4091. Min Act: -0.1700
Data Index: 5511532 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.4091. Min Act: -0.1700
Data Index: 4293777 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.4091. Min Act: -0.1700
Data Index: 2619110 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9091. Min Range: -5.9091
Max Act: 5.3779. Min Act: -0.1700
Data Index: 37635 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19