Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1350 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.2599. Min Act: -0.1700
Data Index: 6872717 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.2911. Min Act: -0.1700
Data Index: 6107933 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.2286. Min Act: -0.1700
Data Index: 6242676 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.1661. Min Act: -0.1700
Data Index: 708323 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.1349. Min Act: -0.1700
Data Index: 1500506 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.1036. Min Act: -0.1700
Data Index: 5956104 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.1036. Min Act: -0.1700
Data Index: 511842 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.1036. Min Act: -0.1700
Data Index: 3255132 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0723. Min Act: -0.1700
Data Index: 4866269 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.1036. Min Act: -0.1700
Data Index: 6242677 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0723. Min Act: -0.1700
Data Index: 6242679 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.1036. Min Act: -0.1700
Data Index: 910720 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0411. Min Act: -0.1700
Data Index: 6213768 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0411. Min Act: -0.1700
Data Index: 5460978 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0723. Min Act: -0.1700
Data Index: 3837954 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0411. Min Act: -0.1700
Data Index: 2249648 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0411. Min Act: -0.1700
Data Index: 6242678 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0411. Min Act: -0.1700
Data Index: 4080241 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0098. Min Act: -0.1700
Data Index: 5503762 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2911. Min Range: -4.2911
Max Act: 4.0098. Min Act: -0.1700
Data Index: 4692999 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19