Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.6484. Min Act: -0.1700
Data Index: 7156343 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.6171. Min Act: -0.1700
Data Index: 1020204 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5545. Min Act: -0.1700
Data Index: 6237033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5231. Min Act: -0.1700
Data Index: 3705560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5231. Min Act: -0.1700
Data Index: 7426172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5231. Min Act: -0.1700
Data Index: 5285476 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 4960374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5231. Min Act: -0.1700
Data Index: 161410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5231. Min Act: -0.1700
Data Index: 4819858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5231. Min Act: -0.1700
Data Index: 4368440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5231. Min Act: -0.1700
Data Index: 7764172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5231. Min Act: -0.1700
Data Index: 1698006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 2653221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 3775143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 6361047 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 3022651 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 2204444 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 2494000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 1415097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4918. Min Act: -0.1700
Data Index: 1626756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19