Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 215 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.2768. Min Act: -0.1700
Data Index: 5503264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.2680. Min Act: -0.1700
Data Index: 1801781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.2768. Min Act: -0.1696
Data Index: 5776520 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.2503. Min Act: -0.1700
Data Index: 78492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.2327. Min Act: -0.1697
Data Index: 3136035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.2151. Min Act: -0.1698
Data Index: 5648207 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.2151. Min Act: -0.1700
Data Index: 8225220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1975. Min Act: -0.1700
Data Index: 5389690 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1887. Min Act: -0.1700
Data Index: 2665750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1799. Min Act: -0.1700
Data Index: 3775508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1799. Min Act: -0.1699
Data Index: 3860979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1799. Min Act: -0.1700
Data Index: 3408940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1887. Min Act: -0.1700
Data Index: 5630063 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1887. Min Act: -0.1700
Data Index: 3284251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1799. Min Act: -0.1700
Data Index: 4645842 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1711. Min Act: -0.1700
Data Index: 5488159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1799. Min Act: -0.1700
Data Index: 4502673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1799. Min Act: -0.1700
Data Index: 3490186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1711. Min Act: -0.1700
Data Index: 5104719 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2768. Min Range: -1.2768
Max Act: 1.1711. Min Act: -0.1700
Data Index: 5772881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19