Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.6076. Min Act: -0.1700
Data Index: 3298138 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.5139. Min Act: -0.1700
Data Index: 7520538 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.3576. Min Act: -0.1700
Data Index: 4443765 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.3889. Min Act: -0.1700
Data Index: 1558666 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.2951. Min Act: -0.1700
Data Index: 1261099 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.2951. Min Act: -0.1700
Data Index: 5573032 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.3264. Min Act: -0.1700
Data Index: 615182 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.2014. Min Act: -0.1700
Data Index: 1820850 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.2014. Min Act: -0.1700
Data Index: 2065771 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.2014. Min Act: -0.1700
Data Index: 2084672 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.2014. Min Act: -0.1700
Data Index: 5708408 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.2014. Min Act: -0.1700
Data Index: 1659892 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.1701. Min Act: -0.1700
Data Index: 6437475 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.1389. Min Act: -0.1700
Data Index: 6669869 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.1389. Min Act: -0.1700
Data Index: 586378 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.1701. Min Act: -0.1700
Data Index: 247934 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.1389. Min Act: -0.1700
Data Index: 5551101 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 2135428 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 3052190 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6076. Min Range: -5.6076
Max Act: 5.1076. Min Act: -0.1700
Data Index: 313153 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19