Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2161 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2375. Min Range: -4.2375
Max Act: 4.2375. Min Act: -0.1700
Data Index: 1888612 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2375. Min Range: -4.2375
Max Act: 4.1125. Min Act: -0.1700
Data Index: 1450623 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2375. Min Range: -4.2375
Max Act: 4.0187. Min Act: -0.1700
Data Index: 6343217 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2375. Min Range: -4.2375
Max Act: 4.0500. Min Act: -0.1700
Data Index: 5075134 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2375. Min Range: -4.2375
Max Act: 4.0500. Min Act: -0.1700
Data Index: 3784295 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2375. Min Range: -4.2375
Max Act: 4.0500. Min Act: -0.1700
Data Index: 5530059 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2375. Min Range: -4.2375
Max Act: 4.0187. Min Act: -0.1700
Data Index: 2520455 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.9875. Min Act: -0.1700
Data Index: 6503038 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.9875. Min Act: -0.1700
Data Index: 1056475 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.9562. Min Act: -0.1700
Data Index: 8168533 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.9562. Min Act: -0.1700
Data Index: 1770972 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.9562. Min Act: -0.1700
Data Index: 2256181 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.9249. Min Act: -0.1700
Data Index: 6240860 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.9249. Min Act: -0.1700
Data Index: 8116493 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.8937. Min Act: -0.1700
Data Index: 6037923 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.8624. Min Act: -0.1700
Data Index: 5846818 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.8624. Min Act: -0.1700
Data Index: 7637717 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.8311. Min Act: -0.1700
Data Index: 221294 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.8311. Min Act: -0.1700
Data Index: 7001650 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2375. Min Range: -4.2375
Max Act: 3.8311. Min Act: -0.1700
Data Index: 908315 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19