Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2407 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6515. Min Act: -0.1700
Data Index: 5511987 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 8169637 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5263. Min Act: -0.1700
Data Index: 7878177 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5106. Min Act: -0.1700
Data Index: 695221 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4950. Min Act: -0.1700
Data Index: 1082824 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4793. Min Act: -0.1700
Data Index: 6149353 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4636. Min Act: -0.1700
Data Index: 1834188 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4323. Min Act: -0.1700
Data Index: 1342781 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4010. Min Act: -0.1700
Data Index: 5851492 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4010. Min Act: -0.1700
Data Index: 8253504 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4010. Min Act: -0.1700
Data Index: 5235019 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4010. Min Act: -0.1700
Data Index: 861864 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.4010. Min Act: -0.1700
Data Index: 5209689 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.3853. Min Act: -0.1700
Data Index: 5633503 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.3539. Min Act: -0.1700
Data Index: 5478791 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.3539. Min Act: -0.1700
Data Index: 4202520 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.3853. Min Act: -0.1700
Data Index: 4297239 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.3539. Min Act: -0.1700
Data Index: 6568135 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.3539. Min Act: -0.1700
Data Index: 4041416 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.3539. Min Act: -0.1700
Data Index: 6942558 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19