Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.9734. Min Act: -0.1700
Data Index: 3019210 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.8172. Min Act: -0.1700
Data Index: 3546878 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.7859. Min Act: -0.1700
Data Index: 603742 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.7547. Min Act: -0.1700
Data Index: 5247555 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.7547. Min Act: -0.1700
Data Index: 1974859 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6922. Min Act: -0.1700
Data Index: 8235156 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.7234. Min Act: -0.1700
Data Index: 70406 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.7234. Min Act: -0.1700
Data Index: 2585421 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6922. Min Act: -0.1700
Data Index: 6896051 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6922. Min Act: -0.1700
Data Index: 5668 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6922. Min Act: -0.1700
Data Index: 2112589 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6922. Min Act: -0.1700
Data Index: 5758183 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6609. Min Act: -0.1700
Data Index: 5923021 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6609. Min Act: -0.1700
Data Index: 6274685 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6609. Min Act: -0.1700
Data Index: 6408897 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6297. Min Act: -0.1700
Data Index: 1970870 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.6297. Min Act: -0.1700
Data Index: 4214621 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.5672. Min Act: -0.1700
Data Index: 6343732 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.5984. Min Act: -0.1700
Data Index: 1306141 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9734. Min Range: -4.9734
Max Act: 4.5984. Min Act: -0.1700
Data Index: 1986333 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19