Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.9115. Min Act: -0.1700
Data Index: 7924983 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.8177. Min Act: -0.1700
Data Index: 632679 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.8177. Min Act: -0.1700
Data Index: 7277969 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.6926. Min Act: -0.1700
Data Index: 2877094 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.6144. Min Act: -0.1700
Data Index: 1061599 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5987. Min Act: -0.1700
Data Index: 3851113 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5831. Min Act: -0.1700
Data Index: 3458597 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5204. Min Act: -0.1700
Data Index: 3223889 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5361. Min Act: -0.1700
Data Index: 4045811 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5361. Min Act: -0.1700
Data Index: 3348118 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5204. Min Act: -0.1700
Data Index: 4986031 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5048. Min Act: -0.1700
Data Index: 5937559 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5048. Min Act: -0.1700
Data Index: 131685 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5048. Min Act: -0.1700
Data Index: 5259391 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.5048. Min Act: -0.1700
Data Index: 4931736 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.4891. Min Act: -0.1700
Data Index: 6623868 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.4891. Min Act: -0.1700
Data Index: 3127426 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.4734. Min Act: -0.1700
Data Index: 2019351 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.4578. Min Act: -0.1700
Data Index: 898304 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9115. Min Range: -3.9115
Max Act: 3.4421. Min Act: -0.1700
Data Index: 6689393 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19