Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.8116. Min Act: -0.1700
Data Index: 1244490 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.4054. Min Act: -0.1700
Data Index: 8598042 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.2804. Min Act: -0.1700
Data Index: 3536294 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.2491. Min Act: -0.1700
Data Index: 7908266 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.1554. Min Act: -0.1700
Data Index: 4110190 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.1241. Min Act: -0.1700
Data Index: 4859850 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.0929. Min Act: -0.1700
Data Index: 602456 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.0929. Min Act: -0.1700
Data Index: 1160934 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.0616. Min Act: -0.1700
Data Index: 5486548 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.0929. Min Act: -0.1700
Data Index: 3869178 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.0616. Min Act: -0.1700
Data Index: 7853684 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8116. Min Range: -5.8116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 4319462 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8116. Min Range: -5.8116
Max Act: 4.9679. Min Act: -0.1700
Data Index: 499194 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8116. Min Range: -5.8116
Max Act: 5.0304. Min Act: -0.1700
Data Index: 2765497 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8116. Min Range: -5.8116
Max Act: 4.9991. Min Act: -0.1700
Data Index: 6580413 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8116. Min Range: -5.8116
Max Act: 4.9679. Min Act: -0.1700
Data Index: 6286092 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8116. Min Range: -5.8116
Max Act: 4.9366. Min Act: -0.1700
Data Index: 2257698 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8116. Min Range: -5.8116
Max Act: 4.9679. Min Act: -0.1700
Data Index: 3387361 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8116. Min Range: -5.8116
Max Act: 4.9679. Min Act: -0.1700
Data Index: 2605339 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8116. Min Range: -5.8116
Max Act: 4.9679. Min Act: -0.1700
Data Index: 1495019 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19