Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3452 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.6031. Min Act: -0.1700
Data Index: 8285252 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.3843. Min Act: -0.1700
Data Index: 825834 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.3218. Min Act: -0.1700
Data Index: 4574982 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.3218. Min Act: -0.1700
Data Index: 4036999 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.2593. Min Act: -0.1700
Data Index: 8681852 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.2281. Min Act: -0.1700
Data Index: 7817979 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1968. Min Act: -0.1700
Data Index: 5453172 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1968. Min Act: -0.1700
Data Index: 1521684 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1968. Min Act: -0.1700
Data Index: 3544020 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1656. Min Act: -0.1700
Data Index: 2337806 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1343. Min Act: -0.1700
Data Index: 7911973 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1031. Min Act: -0.1700
Data Index: 7516517 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1343. Min Act: -0.1700
Data Index: 7125146 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1343. Min Act: -0.1700
Data Index: 815833 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1343. Min Act: -0.1700
Data Index: 5710134 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1343. Min Act: -0.1700
Data Index: 3696846 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1031. Min Act: -0.1700
Data Index: 6246057 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1031. Min Act: -0.1700
Data Index: 6947531 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1343. Min Act: -0.1700
Data Index: 861416 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6031. Min Range: -6.6031
Max Act: 6.1031. Min Act: -0.1700
Data Index: 1495700 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19