Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1570 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2699. Min Range: -6.2699
Max Act: 6.2699. Min Act: -0.1700
Data Index: 3731591 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2699. Min Range: -6.2699
Max Act: 6.0199. Min Act: -0.1700
Data Index: 547791 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9886. Min Act: -0.1700
Data Index: 5842365 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2699. Min Range: -6.2699
Max Act: 6.0511. Min Act: -0.1700
Data Index: 5815734 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9574. Min Act: -0.1700
Data Index: 1137673 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9261. Min Act: -0.1700
Data Index: 3015420 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9261. Min Act: -0.1700
Data Index: 5596560 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9261. Min Act: -0.1700
Data Index: 8600529 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9886. Min Act: -0.1700
Data Index: 7546720 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9574. Min Act: -0.1700
Data Index: 8415439 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9574. Min Act: -0.1700
Data Index: 5914835 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9886. Min Act: -0.1700
Data Index: 256811 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9261. Min Act: -0.1700
Data Index: 4168137 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9886. Min Act: -0.1700
Data Index: 6682041 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9574. Min Act: -0.1700
Data Index: 3753142 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9261. Min Act: -0.1700
Data Index: 71660 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.8949. Min Act: -0.1700
Data Index: 5326167 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.8636. Min Act: -0.1700
Data Index: 1103836 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.9261. Min Act: -0.1700
Data Index: 7362876 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2699. Min Range: -6.2699
Max Act: 5.8324. Min Act: -0.1700
Data Index: 7531978 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19