Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1352 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.1947. Min Range: -3.1947
Max Act: 3.1947. Min Act: -0.1700
Data Index: 8039700 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1947. Min Range: -3.1947
Max Act: 3.0844. Min Act: -0.1700
Data Index: 5852112 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1947. Min Range: -3.1947
Max Act: 3.0529. Min Act: -0.1700
Data Index: 90669 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1947. Min Range: -3.1947
Max Act: 3.0529. Min Act: -0.1700
Data Index: 1209606 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.9897. Min Act: -0.1700
Data Index: 256680 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.9897. Min Act: -0.1700
Data Index: 508485 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.9264. Min Act: -0.1700
Data Index: 2594472 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.9422. Min Act: -0.1700
Data Index: 5344468 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.9422. Min Act: -0.1700
Data Index: 7578156 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.9264. Min Act: -0.1700
Data Index: 8616801 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.9106. Min Act: -0.1700
Data Index: 8397194 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.9106. Min Act: -0.1700
Data Index: 4708250 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.8947. Min Act: -0.1700
Data Index: 5500854 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.8788. Min Act: -0.1700
Data Index: 772714 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.8947. Min Act: -0.1700
Data Index: 5272602 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.8788. Min Act: -0.1700
Data Index: 8418777 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.8630. Min Act: -0.1700
Data Index: 4484164 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.8788. Min Act: -0.1700
Data Index: 7503547 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.8788. Min Act: -0.1700
Data Index: 5243609 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1947. Min Range: -3.1947
Max Act: 2.8471. Min Act: -0.1700
Data Index: 5078646 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19