Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4078 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.9935. Min Act: -0.1700
Data Index: 3729805 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.8060. Min Act: -0.1700
Data Index: 2082480 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.8060. Min Act: -0.1700
Data Index: 3573607 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.7748. Min Act: -0.1700
Data Index: 4621515 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.7435. Min Act: -0.1700
Data Index: 7037867 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.7748. Min Act: -0.1700
Data Index: 1379870 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.7123. Min Act: -0.1700
Data Index: 3202382 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.6810. Min Act: -0.1700
Data Index: 7939347 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.6498. Min Act: -0.1700
Data Index: 4612590 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.6185. Min Act: -0.1700
Data Index: 1423942 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5560. Min Act: -0.1700
Data Index: 7006201 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5560. Min Act: -0.1700
Data Index: 126427 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5560. Min Act: -0.1700
Data Index: 6224949 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4935. Min Act: -0.1700
Data Index: 1230096 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4623. Min Act: -0.1700
Data Index: 3541246 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4623. Min Act: -0.1700
Data Index: 1296661 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4623. Min Act: -0.1700
Data Index: 8640315 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4623. Min Act: -0.1700
Data Index: 1419862 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4623. Min Act: -0.1700
Data Index: 700066 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4623. Min Act: -0.1700
Data Index: 3324570 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19