Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.6071. Min Act: -0.1700
Data Index: 1986932 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.5134. Min Act: -0.1700
Data Index: 8219978 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.4509. Min Act: -0.1700
Data Index: 3066476 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.4509. Min Act: -0.1700
Data Index: 4277536 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.4196. Min Act: -0.1700
Data Index: 6116937 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.4509. Min Act: -0.1700
Data Index: 6372467 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.3884. Min Act: -0.1700
Data Index: 5659935 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.3259. Min Act: -0.1700
Data Index: 2171616 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.3259. Min Act: -0.1700
Data Index: 6116924 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.3259. Min Act: -0.1700
Data Index: 2089335 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2946. Min Act: -0.1700
Data Index: 288085 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2634. Min Act: -0.1700
Data Index: 4683768 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2946. Min Act: -0.1700
Data Index: 7614771 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2634. Min Act: -0.1700
Data Index: 288086 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2634. Min Act: -0.1700
Data Index: 3341646 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2946. Min Act: -0.1700
Data Index: 2591548 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2634. Min Act: -0.1700
Data Index: 4132538 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2634. Min Act: -0.1700
Data Index: 5520974 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2321. Min Act: -0.1700
Data Index: 5733814 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6071. Min Range: -4.6071
Max Act: 4.2946. Min Act: -0.1700
Data Index: 3066477 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19