Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4053 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.8046. Min Act: -0.1700
Data Index: 5853733 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.7734. Min Act: -0.1700
Data Index: 2396512 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.7109. Min Act: -0.1700
Data Index: 5881629 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.6796. Min Act: -0.1700
Data Index: 2675939 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.6171. Min Act: -0.1700
Data Index: 229391 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.5859. Min Act: -0.1700
Data Index: 7059011 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.5546. Min Act: -0.1700
Data Index: 3501252 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.5546. Min Act: -0.1700
Data Index: 7584833 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.4921. Min Act: -0.1700
Data Index: 3156095 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.5234. Min Act: -0.1700
Data Index: 7789093 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.5234. Min Act: -0.1700
Data Index: 487191 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.5234. Min Act: -0.1700
Data Index: 488924 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.5234. Min Act: -0.1700
Data Index: 5360905 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.5234. Min Act: -0.1700
Data Index: 5106906 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.4921. Min Act: -0.1700
Data Index: 7184924 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.4921. Min Act: -0.1700
Data Index: 3489826 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.4609. Min Act: -0.1700
Data Index: 4399301 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.4609. Min Act: -0.1700
Data Index: 3973969 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.4609. Min Act: -0.1700
Data Index: 346584 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8046. Min Range: -4.8046
Max Act: 4.4296. Min Act: -0.1700
Data Index: 4745818 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19