Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2102 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.4609. Min Act: -0.1700
Data Index: 8065990 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.4453. Min Act: -0.1700
Data Index: 6774000 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.4296. Min Act: -0.1700
Data Index: 2469808 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.4139. Min Act: -0.1700
Data Index: 8324548 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3982. Min Act: -0.1700
Data Index: 8427397 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3982. Min Act: -0.1700
Data Index: 4953326 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3669. Min Act: -0.1700
Data Index: 2348775 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3826. Min Act: -0.1700
Data Index: 6278907 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3826. Min Act: -0.1700
Data Index: 1868852 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3669. Min Act: -0.1700
Data Index: 4615043 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3669. Min Act: -0.1700
Data Index: 4705871 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3669. Min Act: -0.1700
Data Index: 914442 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3669. Min Act: -0.1700
Data Index: 3136061 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3669. Min Act: -0.1700
Data Index: 3069674 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3512. Min Act: -0.1700
Data Index: 4687420 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3669. Min Act: -0.1700
Data Index: 2555342 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3669. Min Act: -0.1700
Data Index: 6292119 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3512. Min Act: -0.1700
Data Index: 8634685 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3512. Min Act: -0.1700
Data Index: 1965719 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4609. Min Range: -3.4609
Max Act: 3.3512. Min Act: -0.1700
Data Index: 2132170 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19