Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 366 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.6642. Min Act: -0.1700
Data Index: 7499121 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.6330. Min Act: -0.1700
Data Index: 6684930 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.5080. Min Act: -0.1700
Data Index: 8668614 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.5080. Min Act: -0.1700
Data Index: 4218855 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.4142. Min Act: -0.1700
Data Index: 1309696 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.2580. Min Act: -0.1700
Data Index: 6232517 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.2267. Min Act: -0.1700
Data Index: 4622876 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.2267. Min Act: -0.1700
Data Index: 6779071 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.2267. Min Act: -0.1700
Data Index: 8664539 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.1955. Min Act: -0.1700
Data Index: 5666421 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.1955. Min Act: -0.1700
Data Index: 7999296 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.2267. Min Act: -0.1700
Data Index: 7714796 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.1642. Min Act: -0.1700
Data Index: 1405696 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.1955. Min Act: -0.1700
Data Index: 4817310 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.2267. Min Act: -0.1700
Data Index: 4665256 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.2267. Min Act: -0.1700
Data Index: 116840 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.1642. Min Act: -0.1700
Data Index: 6204652 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.1642. Min Act: -0.1700
Data Index: 4309269 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.1642. Min Act: -0.1700
Data Index: 1295049 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6642. Min Range: -7.6642
Max Act: 7.1642. Min Act: -0.1700
Data Index: 7125256 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19