Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.9586. Min Act: -0.1700
Data Index: 2005747 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.8336. Min Act: -0.1700
Data Index: 1503063 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.7086. Min Act: -0.1700
Data Index: 5372130 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.5836. Min Act: -0.1700
Data Index: 1121126 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.5836. Min Act: -0.1700
Data Index: 2418071 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.4586. Min Act: -0.1700
Data Index: 887180 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.4586. Min Act: -0.1700
Data Index: 6555166 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.3336. Min Act: -0.1700
Data Index: 369601 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.3336. Min Act: -0.1700
Data Index: 5372126 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.3336. Min Act: -0.1700
Data Index: 7001219 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.3336. Min Act: -0.1700
Data Index: 4025056 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.3336. Min Act: -0.1700
Data Index: 4100390 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.3336. Min Act: -0.1700
Data Index: 4554718 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.2086. Min Act: -0.1700
Data Index: 2633198 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.2086. Min Act: -0.1700
Data Index: 5372128 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.2086. Min Act: -0.1700
Data Index: 7385203 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.2086. Min Act: -0.1700
Data Index: 4003407 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.2086. Min Act: -0.1700
Data Index: 6073139 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.2086. Min Act: -0.1700
Data Index: 978522 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.9586. Min Range: -17.9586
Max Act: 17.2086. Min Act: -0.1700
Data Index: 3765695 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19