Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3746 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.9944. Min Act: -0.1700
Data Index: 2795121 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.8381. Min Act: -0.1700
Data Index: 835134 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.8069. Min Act: -0.1700
Data Index: 6780471 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.7756. Min Act: -0.1700
Data Index: 2650040 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.7444. Min Act: -0.1700
Data Index: 5261016 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.7444. Min Act: -0.1700
Data Index: 47943 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.7131. Min Act: -0.1700
Data Index: 524660 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.7131. Min Act: -0.1700
Data Index: 5319512 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.6819. Min Act: -0.1700
Data Index: 4823584 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.6819. Min Act: -0.1700
Data Index: 4465581 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.6819. Min Act: -0.1700
Data Index: 2287440 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.6506. Min Act: -0.1700
Data Index: 2720280 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.6506. Min Act: -0.1700
Data Index: 6759179 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.6193. Min Act: -0.1700
Data Index: 6205079 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.6193. Min Act: -0.1700
Data Index: 2806125 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.6193. Min Act: -0.1700
Data Index: 1944681 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.5881. Min Act: -0.1700
Data Index: 6003753 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.5568. Min Act: -0.1700
Data Index: 1336229 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.5568. Min Act: -0.1700
Data Index: 1463307 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9944. Min Range: -4.9944
Max Act: 4.5881. Min Act: -0.1700
Data Index: 5016012 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19