Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.4949. Min Act: -0.1700
Data Index: 8245160 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.2761. Min Act: -0.1700
Data Index: 39943 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.2449. Min Act: -0.1700
Data Index: 3479243 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.1823. Min Act: -0.1700
Data Index: 1094078 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.0886. Min Act: -0.1700
Data Index: 3101071 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.0261. Min Act: -0.1700
Data Index: 8816927 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.0573. Min Act: -0.1700
Data Index: 8770578 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.0573. Min Act: -0.1700
Data Index: 2922765 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.0261. Min Act: -0.1700
Data Index: 4015064 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.0261. Min Act: -0.1700
Data Index: 7886744 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.0261. Min Act: -0.1700
Data Index: 1518251 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4949. Min Range: -4.4949
Max Act: 4.0261. Min Act: -0.1700
Data Index: 6570454 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4949. Min Range: -4.4949
Max Act: 3.9635. Min Act: -0.1700
Data Index: 6074028 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4949. Min Range: -4.4949
Max Act: 3.9948. Min Act: -0.1700
Data Index: 531869 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4949. Min Range: -4.4949
Max Act: 3.9948. Min Act: -0.1700
Data Index: 1991936 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4949. Min Range: -4.4949
Max Act: 3.9948. Min Act: -0.1700
Data Index: 6478244 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4949. Min Range: -4.4949
Max Act: 3.9948. Min Act: -0.1700
Data Index: 5889292 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4949. Min Range: -4.4949
Max Act: 3.9948. Min Act: -0.1700
Data Index: 3563605 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4949. Min Range: -4.4949
Max Act: 3.9948. Min Act: -0.1700
Data Index: 5876751 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4949. Min Range: -4.4949
Max Act: 3.9635. Min Act: -0.1700
Data Index: 996960 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19