Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.2285. Min Act: -0.1700
Data Index: 4602784 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1845. Min Act: -0.1700
Data Index: 2808448 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1493. Min Act: -0.1700
Data Index: 705253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1493. Min Act: -0.1700
Data Index: 3727436 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1493. Min Act: -0.1700
Data Index: 8429565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1405. Min Act: -0.1700
Data Index: 2260126 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1405. Min Act: -0.1700
Data Index: 4189432 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1405. Min Act: -0.1700
Data Index: 1398480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1405. Min Act: -0.1700
Data Index: 3000283 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1317. Min Act: -0.1700
Data Index: 301379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1317. Min Act: -0.1700
Data Index: 3300915 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1230. Min Act: -0.1700
Data Index: 3237738 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1317. Min Act: -0.1700
Data Index: 8606451 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1142. Min Act: -0.1700
Data Index: 5444895 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1230. Min Act: -0.1700
Data Index: 459282 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1230. Min Act: -0.1700
Data Index: 7390565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1054. Min Act: -0.1700
Data Index: 2080627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1230. Min Act: -0.1700
Data Index: 2939411 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.1230. Min Act: -0.1700
Data Index: 5177893 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2285. Min Range: -1.2285
Max Act: 1.0967. Min Act: -0.1700
Data Index: 3282984 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19