Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 11 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.6043. Min Act: -0.1700
Data Index: 4409798 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.5106. Min Act: -0.1700
Data Index: 336685 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.5106. Min Act: -0.1700
Data Index: 8004065 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.3856. Min Act: -0.1700
Data Index: 761969 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.2293. Min Act: -0.1700
Data Index: 7007753 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.1356. Min Act: -0.1700
Data Index: 449541 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.1356. Min Act: -0.1700
Data Index: 7548292 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.1043. Min Act: -0.1700
Data Index: 113445 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.1043. Min Act: -0.1700
Data Index: 1740366 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.0106. Min Act: -0.1700
Data Index: 2317614 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6043. Min Range: -7.6043
Max Act: 7.0106. Min Act: -0.1700
Data Index: 6380433 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.9793. Min Act: -0.1700
Data Index: 6051403 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.9793. Min Act: -0.1700
Data Index: 7818852 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.9168. Min Act: -0.1700
Data Index: 3214514 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.8543. Min Act: -0.1700
Data Index: 6654580 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.8231. Min Act: -0.1700
Data Index: 5519070 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.7918. Min Act: -0.1700
Data Index: 4685251 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.7606. Min Act: -0.1700
Data Index: 5495548 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.8231. Min Act: -0.1700
Data Index: 871701 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6043. Min Range: -7.6043
Max Act: 6.7918. Min Act: -0.1700
Data Index: 5566691 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19