Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2747 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2492. Min Act: -0.1700
Data Index: 1467619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2492. Min Act: -0.1700
Data Index: 3274357 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2492. Min Act: -0.1700
Data Index: 4803966 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2492. Min Act: -0.1700
Data Index: 293994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2492. Min Act: -0.1700
Data Index: 4809324 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 2960476 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 5113028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 2913811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 2048283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 884025 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 8019267 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 7507902 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 7391298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 7013133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 6664916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.2179. Min Act: -0.1700
Data Index: 5694782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.1867. Min Act: -0.1700
Data Index: 3465054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.1867. Min Act: -0.1700
Data Index: 1030388 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.1867. Min Act: -0.1700
Data Index: 3569585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2492. Min Range: -4.2492
Max Act: 4.1867. Min Act: -0.1700
Data Index: 5065865 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19