Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 898 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.3086. Min Act: -0.1700
Data Index: 2442465 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.3086. Min Act: -0.1700
Data Index: 5900829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.3086. Min Act: -0.1700
Data Index: 1047982 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.3086. Min Act: -0.1700
Data Index: 7386745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.2149. Min Act: -0.1700
Data Index: 2082465 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.1524. Min Act: -0.1700
Data Index: 1943496 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.1211. Min Act: -0.1700
Data Index: 2182733 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.0899. Min Act: -0.1700
Data Index: 8164480 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.0899. Min Act: -0.1700
Data Index: 4614519 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.0899. Min Act: -0.1700
Data Index: 2264949 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.0899. Min Act: -0.1700
Data Index: 1899072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3086. Min Range: -5.3086
Max Act: 5.0899. Min Act: -0.1700
Data Index: 5584505 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3086. Min Range: -5.3086
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6969336 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3086. Min Range: -5.3086
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6639604 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3086. Min Range: -5.3086
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6297483 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3086. Min Range: -5.3086
Max Act: 4.9961. Min Act: -0.1700
Data Index: 4340209 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3086. Min Range: -5.3086
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6630812 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3086. Min Range: -5.3086
Max Act: 4.9649. Min Act: -0.1700
Data Index: 5589755 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3086. Min Range: -5.3086
Max Act: 4.9649. Min Act: -0.1700
Data Index: 3644471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3086. Min Range: -5.3086
Max Act: 4.9649. Min Act: -0.1700
Data Index: 5957104 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19