Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4365 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.5826. Min Act: -0.1700
Data Index: 7467580 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.4263. Min Act: -0.1700
Data Index: 7387455 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.3638. Min Act: -0.1700
Data Index: 6860429 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.3638. Min Act: -0.1700
Data Index: 1486640 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.3013. Min Act: -0.1700
Data Index: 1070020 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 1850799 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 1800301 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 2900987 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 2806696 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 1593180 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 2752111 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 81617 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 2662927 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 1421270 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 2608170 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 1153782 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 2573471 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 974356 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 972944 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5826. Min Range: -4.5826
Max Act: 4.2388. Min Act: -0.1700
Data Index: 2529935 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19