Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3833 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0953. Min Range: -7.0953
Max Act: 7.0953. Min Act: -0.1700
Data Index: 3287542 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.9703. Min Act: -0.1700
Data Index: 674387 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.9078. Min Act: -0.1700
Data Index: 6906819 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.9078. Min Act: -0.1700
Data Index: 8793649 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.9078. Min Act: -0.1700
Data Index: 7248797 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.8140. Min Act: -0.1700
Data Index: 2388807 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7515. Min Act: -0.1700
Data Index: 4667195 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7203. Min Act: -0.1700
Data Index: 6245096 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7203. Min Act: -0.1700
Data Index: 5956214 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7203. Min Act: -0.1700
Data Index: 1026127 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6890. Min Act: -0.1700
Data Index: 988939 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.7203. Min Act: -0.1700
Data Index: 8095673 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 6599511 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.6265. Min Act: -0.1700
Data Index: 8751504 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.5953. Min Act: -0.1700
Data Index: 8777832 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.5640. Min Act: -0.1700
Data Index: 502134 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.5953. Min Act: -0.1700
Data Index: 375132 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.5953. Min Act: -0.1700
Data Index: 3322497 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.5953. Min Act: -0.1700
Data Index: 2508378 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0953. Min Range: -7.0953
Max Act: 6.5953. Min Act: -0.1700
Data Index: 893294 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19