Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 320 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.5019. Min Act: -0.1700
Data Index: 7892313 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3769. Min Act: -0.1700
Data Index: 3525634 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3769. Min Act: -0.1700
Data Index: 5893087 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.4082. Min Act: -0.1700
Data Index: 5389733 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2206. Min Act: -0.1700
Data Index: 7449024 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2519. Min Act: -0.1700
Data Index: 7553592 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.3144. Min Act: -0.1700
Data Index: 666593 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1894. Min Act: -0.1700
Data Index: 4512592 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2206. Min Act: -0.1700
Data Index: 115195 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.2206. Min Act: -0.1700
Data Index: 3672733 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 5478269 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 4458552 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 1800879 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 2821975 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1894. Min Act: -0.1700
Data Index: 4364304 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 345892 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1269. Min Act: -0.1700
Data Index: 6758379 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.0644. Min Act: -0.1700
Data Index: 5439558 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1894. Min Act: -0.1700
Data Index: 5754227 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5019. Min Range: -4.5019
Max Act: 4.1581. Min Act: -0.1700
Data Index: 5464579 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19