Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1152 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0535. Min Range: -5.0535
Max Act: 5.0535. Min Act: -0.1700
Data Index: 6709988 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8660. Min Act: -0.1700
Data Index: 4425067 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.9285. Min Act: -0.1700
Data Index: 6216010 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8660. Min Act: -0.1700
Data Index: 3103397 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8973. Min Act: -0.1700
Data Index: 261930 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8348. Min Act: -0.1700
Data Index: 8108938 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8973. Min Act: -0.1700
Data Index: 3103411 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8348. Min Act: -0.1700
Data Index: 5445605 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8348. Min Act: -0.1700
Data Index: 1987832 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8035. Min Act: -0.1700
Data Index: 6642003 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8035. Min Act: -0.1700
Data Index: 8108931 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.8035. Min Act: -0.1700
Data Index: 313378 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.7723. Min Act: -0.1700
Data Index: 5925066 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.7410. Min Act: -0.1700
Data Index: 396614 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.7723. Min Act: -0.1700
Data Index: 8366104 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.7410. Min Act: -0.1700
Data Index: 3904072 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.7410. Min Act: -0.1700
Data Index: 2102889 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.7410. Min Act: -0.1700
Data Index: 1166439 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.7410. Min Act: -0.1700
Data Index: 874513 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0535. Min Range: -5.0535
Max Act: 4.7098. Min Act: -0.1700
Data Index: 2937175 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19