Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1142. Min Range: -6.1142
Max Act: 6.1142. Min Act: -0.1700
Data Index: 3907223 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.9267. Min Act: -0.1700
Data Index: 2355355 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8330. Min Act: -0.1700
Data Index: 1586729 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.8017. Min Act: -0.1700
Data Index: 2820227 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.6767. Min Act: -0.1700
Data Index: 528754 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.6767. Min Act: -0.1700
Data Index: 3835129 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.6455. Min Act: -0.1700
Data Index: 3607641 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.6455. Min Act: -0.1700
Data Index: 5804977 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.6455. Min Act: -0.1700
Data Index: 2316702 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5830. Min Act: -0.1700
Data Index: 2486377 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5830. Min Act: -0.1700
Data Index: 6679479 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5830. Min Act: -0.1700
Data Index: 8066568 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5830. Min Act: -0.1700
Data Index: 8407790 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5830. Min Act: -0.1700
Data Index: 1119627 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5517. Min Act: -0.1700
Data Index: 7773604 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5830. Min Act: -0.1700
Data Index: 7752835 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5205. Min Act: -0.1700
Data Index: 5050815 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.5205. Min Act: -0.1700
Data Index: 8455097 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.4892. Min Act: -0.1700
Data Index: 4859370 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1142. Min Range: -6.1142
Max Act: 5.4892. Min Act: -0.1700
Data Index: 7341835 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19