Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.3556. Min Act: -0.1700
Data Index: 8044650 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.3244. Min Act: -0.1700
Data Index: 1068884 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.2619. Min Act: -0.1700
Data Index: 3971806 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.2306. Min Act: -0.1700
Data Index: 29823 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.1994. Min Act: -0.1700
Data Index: 63129 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.1994. Min Act: -0.1700
Data Index: 1276773 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.1681. Min Act: -0.1700
Data Index: 8631328 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.1994. Min Act: -0.1700
Data Index: 2268181 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.1369. Min Act: -0.1700
Data Index: 5724606 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.1369. Min Act: -0.1700
Data Index: 4131896 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.1056. Min Act: -0.1700
Data Index: 2171514 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.1056. Min Act: -0.1700
Data Index: 8721797 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.0744. Min Act: -0.1700
Data Index: 6164306 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.0744. Min Act: -0.1700
Data Index: 3265116 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.0431. Min Act: -0.1700
Data Index: 1286547 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.0119. Min Act: -0.1700
Data Index: 3204528 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.0119. Min Act: -0.1700
Data Index: 5223296 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.0119. Min Act: -0.1700
Data Index: 8044990 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3556. Min Range: -6.3556
Max Act: 6.0119. Min Act: -0.1700
Data Index: 3547171 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3556. Min Range: -6.3556
Max Act: 5.9494. Min Act: -0.1700
Data Index: 5521047 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19