Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.1767. Min Act: -0.1700
Data Index: 3518086 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.1925. Min Act: -0.1700
Data Index: 4836944 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.1767. Min Act: -0.1700
Data Index: 1113865 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.1295. Min Act: -0.1700
Data Index: 2783862 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.1453. Min Act: -0.1700
Data Index: 3797788 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.1138. Min Act: -0.1700
Data Index: 4127894 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.1138. Min Act: -0.1700
Data Index: 7641100 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.0980. Min Act: -0.1700
Data Index: 308216 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.0980. Min Act: -0.1700
Data Index: 2891834 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.0980. Min Act: -0.1700
Data Index: 5993540 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.0507. Min Act: -0.1700
Data Index: 1388065 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.0349. Min Act: -0.1700
Data Index: 2555675 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.0349. Min Act: -0.1700
Data Index: 1493220 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.0191. Min Act: -0.1700
Data Index: 4199123 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1925. Min Range: -3.1925
Max Act: 2.9875. Min Act: -0.1700
Data Index: 4945467 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1925. Min Range: -3.1925
Max Act: 3.0191. Min Act: -0.1700
Data Index: 6440008 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1925. Min Range: -3.1925
Max Act: 2.9875. Min Act: -0.1700
Data Index: 2726652 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1925. Min Range: -3.1925
Max Act: 2.9875. Min Act: -0.1700
Data Index: 3799242 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1925. Min Range: -3.1925
Max Act: 2.9717. Min Act: -0.1700
Data Index: 6124489 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1925. Min Range: -3.1925
Max Act: 2.9559. Min Act: -0.1700
Data Index: 6613325 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19