Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6105. Min Range: -6.6105
Max Act: 6.6105. Min Act: -0.1700
Data Index: 8223629 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6105. Min Range: -6.6105
Max Act: 6.2355. Min Act: -0.1700
Data Index: 4209551 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6105. Min Range: -6.6105
Max Act: 6.1105. Min Act: -0.1700
Data Index: 7985487 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6105. Min Range: -6.6105
Max Act: 6.0168. Min Act: -0.1700
Data Index: 4129234 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6105. Min Range: -6.6105
Max Act: 6.0168. Min Act: -0.1700
Data Index: 783130 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.9855. Min Act: -0.1700
Data Index: 5018895 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.9543. Min Act: -0.1700
Data Index: 8542254 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.9543. Min Act: -0.1700
Data Index: 4230855 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.9543. Min Act: -0.1700
Data Index: 1403956 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 4047697 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 3301503 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.9230. Min Act: -0.1700
Data Index: 941869 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.8605. Min Act: -0.1700
Data Index: 8095964 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.8605. Min Act: -0.1700
Data Index: 3188023 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.8293. Min Act: -0.1700
Data Index: 979205 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.8293. Min Act: -0.1700
Data Index: 5487887 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.7980. Min Act: -0.1700
Data Index: 7501989 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.7980. Min Act: -0.1700
Data Index: 3783112 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.7980. Min Act: -0.1700
Data Index: 1799055 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6105. Min Range: -6.6105
Max Act: 5.7668. Min Act: -0.1700
Data Index: 5138092 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19