Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2391. Min Range: -5.2391
Max Act: 5.2391. Min Act: -0.1700
Data Index: 5675578 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2391. Min Range: -5.2391
Max Act: 5.1141. Min Act: -0.1700
Data Index: 4939474 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2391. Min Range: -5.2391
Max Act: 5.0828. Min Act: -0.1700
Data Index: 77893 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2391. Min Range: -5.2391
Max Act: 5.0516. Min Act: -0.1700
Data Index: 2699521 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.9266. Min Act: -0.1700
Data Index: 4219325 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.9266. Min Act: -0.1700
Data Index: 698814 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.9266. Min Act: -0.1700
Data Index: 503317 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8953. Min Act: -0.1700
Data Index: 1678210 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1187054 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8328. Min Act: -0.1700
Data Index: 3036704 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8328. Min Act: -0.1700
Data Index: 3036702 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8016. Min Act: -0.1700
Data Index: 1139375 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.7703. Min Act: -0.1700
Data Index: 2133403 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8016. Min Act: -0.1700
Data Index: 1639224 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8016. Min Act: -0.1700
Data Index: 6386345 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8016. Min Act: -0.1700
Data Index: 4919964 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8016. Min Act: -0.1700
Data Index: 8339748 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8016. Min Act: -0.1700
Data Index: 161617 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.7391. Min Act: -0.1700
Data Index: 755938 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2391. Min Range: -5.2391
Max Act: 4.8016. Min Act: -0.1700
Data Index: 2663989 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19