Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2381 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.6921. Min Act: -0.1700
Data Index: 4018282 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.5984. Min Act: -0.1700
Data Index: 8189727 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.5671. Min Act: -0.1700
Data Index: 2098449 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.5359. Min Act: -0.1700
Data Index: 6873965 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.5359. Min Act: -0.1700
Data Index: 7877156 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.5359. Min Act: -0.1700
Data Index: 8150431 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.5359. Min Act: -0.1700
Data Index: 5004480 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4734. Min Act: -0.1700
Data Index: 840920 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.5359. Min Act: -0.1700
Data Index: 2356679 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.5359. Min Act: -0.1700
Data Index: 1816715 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4734. Min Act: -0.1700
Data Index: 2359466 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4421. Min Act: -0.1700
Data Index: 1159034 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4421. Min Act: -0.1700
Data Index: 2165534 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4421. Min Act: -0.1700
Data Index: 8164620 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4421. Min Act: -0.1700
Data Index: 6275735 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4421. Min Act: -0.1700
Data Index: 6138097 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4109. Min Act: -0.1700
Data Index: 6923895 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4734. Min Act: -0.1700
Data Index: 8168512 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4109. Min Act: -0.1700
Data Index: 3764606 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6921. Min Range: -5.6921
Max Act: 5.4421. Min Act: -0.1700
Data Index: 1865725 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19