Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0122. Min Range: -7.0122
Max Act: 7.0122. Min Act: -0.1700
Data Index: 3827274 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.7310. Min Act: -0.1700
Data Index: 8359340 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.6997. Min Act: -0.1700
Data Index: 170202 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.6997. Min Act: -0.1700
Data Index: 8665842 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.7622. Min Act: -0.1700
Data Index: 4251630 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.6685. Min Act: -0.1700
Data Index: 3279040 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.6685. Min Act: -0.1700
Data Index: 6506013 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5747. Min Act: -0.1700
Data Index: 7533345 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.6060. Min Act: -0.1700
Data Index: 7522864 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.6060. Min Act: -0.1700
Data Index: 6216444 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.6060. Min Act: -0.1700
Data Index: 2566534 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5435. Min Act: -0.1700
Data Index: 5906855 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5435. Min Act: -0.1700
Data Index: 7533359 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5122. Min Act: -0.1700
Data Index: 2254564 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5435. Min Act: -0.1700
Data Index: 3396075 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5122. Min Act: -0.1700
Data Index: 5906864 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5122. Min Act: -0.1700
Data Index: 5275979 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5435. Min Act: -0.1700
Data Index: 4599582 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.5122. Min Act: -0.1700
Data Index: 6216445 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0122. Min Range: -7.0122
Max Act: 6.4810. Min Act: -0.1700
Data Index: 3108582 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19