Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4942. Min Act: -0.1700
Data Index: 4797639 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4780564 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4482848 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4821825 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 2222251 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 3005139 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 2033021 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 3544763 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 1624407 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 3267586 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 2217557 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 2401544 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4124165 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 1857655 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4916310 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4801872 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 1857249 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 4110573 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 3710232 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4942. Min Range: -4.4942
Max Act: 4.4005. Min Act: -0.1700
Data Index: 1646950 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19