Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0482. Min Range: -6.0482
Max Act: 6.0482. Min Act: -0.1700
Data Index: 5315205 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9857. Min Act: -0.1700
Data Index: 5195556 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.9545. Min Act: -0.1700
Data Index: 2012267 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8920. Min Act: -0.1700
Data Index: 5195560 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8607. Min Act: -0.1700
Data Index: 784019 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8607. Min Act: -0.1700
Data Index: 6903142 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.8295. Min Act: -0.1700
Data Index: 7898522 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.7982. Min Act: -0.1700
Data Index: 5195546 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.7982. Min Act: -0.1700
Data Index: 4052331 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.7357. Min Act: -0.1700
Data Index: 5195548 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.7357. Min Act: -0.1700
Data Index: 3240217 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.7045. Min Act: -0.1700
Data Index: 8477509 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.7045. Min Act: -0.1700
Data Index: 6164691 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.6732. Min Act: -0.1700
Data Index: 5660976 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.7045. Min Act: -0.1700
Data Index: 173645 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.6732. Min Act: -0.1700
Data Index: 1191758 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.6420. Min Act: -0.1700
Data Index: 4158242 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.6420. Min Act: -0.1700
Data Index: 918307 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.6420. Min Act: -0.1700
Data Index: 2878531 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0482. Min Range: -6.0482
Max Act: 5.6107. Min Act: -0.1700
Data Index: 7760475 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19