Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.7968. Min Act: -0.1700
Data Index: 502968 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.7343. Min Act: -0.1700
Data Index: 4721409 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.5468. Min Act: -0.1700
Data Index: 3975595 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.4530. Min Act: -0.1700
Data Index: 6304885 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.4218. Min Act: -0.1700
Data Index: 4095807 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.3905. Min Act: -0.1700
Data Index: 8173928 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.3905. Min Act: -0.1700
Data Index: 6804303 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.2343. Min Act: -0.1700
Data Index: 8534306 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.2343. Min Act: -0.1700
Data Index: 1100594 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.2343. Min Act: -0.1700
Data Index: 6495896 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.2030. Min Act: -0.1700
Data Index: 4022487 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.2030. Min Act: -0.1700
Data Index: 5683338 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.1718. Min Act: -0.1700
Data Index: 8306226 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.1718. Min Act: -0.1700
Data Index: 1976565 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.1405. Min Act: -0.1700
Data Index: 8334877 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.1405. Min Act: -0.1700
Data Index: 6390490 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.1405. Min Act: -0.1700
Data Index: 2770492 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.1718. Min Act: -0.1700
Data Index: 1554640 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.1093. Min Act: -0.1700
Data Index: 3401572 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7968. Min Range: -7.7968
Max Act: 7.1093. Min Act: -0.1700
Data Index: 7954436 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19