Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 76 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3201. Min Range: -5.3201
Max Act: 5.3201. Min Act: -0.1700
Data Index: 748312 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3201. Min Range: -5.3201
Max Act: 5.1326. Min Act: -0.1700
Data Index: 5289041 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.9138. Min Act: -0.1700
Data Index: 2541675 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.8513. Min Act: -0.1700
Data Index: 2477711 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.8201. Min Act: -0.1700
Data Index: 6153119 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.8201. Min Act: -0.1700
Data Index: 6153125 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.7888. Min Act: -0.1700
Data Index: 4200381 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.7888. Min Act: -0.1700
Data Index: 2541668 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.7576. Min Act: -0.1700
Data Index: 6765112 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.7576. Min Act: -0.1700
Data Index: 4800916 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.7263. Min Act: -0.1700
Data Index: 6153126 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.6951. Min Act: -0.1700
Data Index: 4301999 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.6951. Min Act: -0.1700
Data Index: 2541687 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.6638. Min Act: -0.1700
Data Index: 2541659 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.6013. Min Act: -0.1700
Data Index: 6153137 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.5701. Min Act: -0.1700
Data Index: 2541674 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.5701. Min Act: -0.1700
Data Index: 2541673 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.5701. Min Act: -0.1700
Data Index: 3730909 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.5701. Min Act: -0.1700
Data Index: 2541662 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3201. Min Range: -5.3201
Max Act: 4.5701. Min Act: -0.1700
Data Index: 2541669 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19