Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.6972. Min Act: -0.1700
Data Index: 6277798 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.4160. Min Act: -0.1700
Data Index: 6044813 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.1660. Min Act: -0.1700
Data Index: 1562741 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.1035. Min Act: -0.1700
Data Index: 6862427 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.1035. Min Act: -0.1700
Data Index: 5953864 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.0722. Min Act: -0.1700
Data Index: 3570602 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.0722. Min Act: -0.1700
Data Index: 5128015 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.0097. Min Act: -0.1700
Data Index: 4491932 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.0097. Min Act: -0.1700
Data Index: 4856546 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.0097. Min Act: -0.1700
Data Index: 1061880 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6972. Min Range: -5.6972
Max Act: 4.9785. Min Act: -0.1700
Data Index: 5806825 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.0097. Min Act: -0.1700
Data Index: 1658859 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6972. Min Range: -5.6972
Max Act: 5.0097. Min Act: -0.1700
Data Index: 7765461 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6972. Min Range: -5.6972
Max Act: 4.9785. Min Act: -0.1700
Data Index: 4140245 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6972. Min Range: -5.6972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 4272614 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6972. Min Range: -5.6972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 250809 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6972. Min Range: -5.6972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 6707680 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6972. Min Range: -5.6972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 22143 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6972. Min Range: -5.6972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 5227322 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6972. Min Range: -5.6972
Max Act: 4.9160. Min Act: -0.1700
Data Index: 1629152 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19