Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6094. Min Range: -5.6094
Max Act: 5.6094. Min Act: -0.1700
Data Index: 5254599 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6094. Min Range: -5.6094
Max Act: 5.5782. Min Act: -0.1700
Data Index: 1796949 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6094. Min Range: -5.6094
Max Act: 5.5157. Min Act: -0.1700
Data Index: 323932 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6094. Min Range: -5.6094
Max Act: 5.3594. Min Act: -0.1700
Data Index: 4669583 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6094. Min Range: -5.6094
Max Act: 5.1407. Min Act: -0.1700
Data Index: 5717254 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6094. Min Range: -5.6094
Max Act: 5.1094. Min Act: -0.1700
Data Index: 2729602 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6094. Min Range: -5.6094
Max Act: 5.0782. Min Act: -0.1700
Data Index: 3101116 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6094. Min Range: -5.6094
Max Act: 5.0469. Min Act: -0.1700
Data Index: 4570661 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.9844. Min Act: -0.1700
Data Index: 4121253 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.9219. Min Act: -0.1700
Data Index: 225641 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.9219. Min Act: -0.1700
Data Index: 6215807 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8594. Min Act: -0.1700
Data Index: 4137296 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8907. Min Act: -0.1700
Data Index: 7684793 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8907. Min Act: -0.1700
Data Index: 3678699 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8907. Min Act: -0.1700
Data Index: 8027203 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8594. Min Act: -0.1700
Data Index: 7806218 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8594. Min Act: -0.1700
Data Index: 7283089 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8594. Min Act: -0.1700
Data Index: 246266 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8594. Min Act: -0.1700
Data Index: 7093005 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6094. Min Range: -5.6094
Max Act: 4.8282. Min Act: -0.1700
Data Index: 3626465 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19