Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 839 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.7054. Min Act: -0.1700
Data Index: 4010994 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.4241. Min Act: -0.1700
Data Index: 4152656 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.4554. Min Act: -0.1700
Data Index: 5770714 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.3616. Min Act: -0.1700
Data Index: 2573025 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.3616. Min Act: -0.1700
Data Index: 8417516 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2366. Min Act: -0.1700
Data Index: 4839072 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2366. Min Act: -0.1700
Data Index: 2737220 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2679. Min Act: -0.1700
Data Index: 2419565 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2054. Min Act: -0.1700
Data Index: 3475358 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2366. Min Act: -0.1700
Data Index: 7306782 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2366. Min Act: -0.1700
Data Index: 6451472 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2054. Min Act: -0.1700
Data Index: 4467694 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2054. Min Act: -0.1700
Data Index: 4792948 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.2054. Min Act: -0.1700
Data Index: 2517875 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.1741. Min Act: -0.1700
Data Index: 2565396 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.1116. Min Act: -0.1700
Data Index: 983244 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.1429. Min Act: -0.1700
Data Index: 2583252 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.1429. Min Act: -0.1700
Data Index: 4386843 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.1116. Min Act: -0.1700
Data Index: 5399281 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7054. Min Range: -5.7054
Max Act: 5.0491. Min Act: -0.1700
Data Index: 6451055 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19