Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1409 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.4326. Min Act: -0.1700
Data Index: 7109252 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.4326. Min Act: -0.1700
Data Index: 2324254 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.4014. Min Act: -0.1700
Data Index: 1480680 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.3389. Min Act: -0.1700
Data Index: 1631992 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.2451. Min Act: -0.1700
Data Index: 1063847 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.2139. Min Act: -0.1700
Data Index: 6480316 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.2139. Min Act: -0.1700
Data Index: 274577 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.1826. Min Act: -0.1700
Data Index: 8420902 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.1826. Min Act: -0.1700
Data Index: 462810 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.1826. Min Act: -0.1700
Data Index: 1705278 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.1514. Min Act: -0.1700
Data Index: 1894043 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.1514. Min Act: -0.1700
Data Index: 1460174 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.1201. Min Act: -0.1700
Data Index: 5683472 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.1201. Min Act: -0.1700
Data Index: 5385185 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.0889. Min Act: -0.1700
Data Index: 6269146 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.0889. Min Act: -0.1700
Data Index: 6330571 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.0889. Min Act: -0.1700
Data Index: 1703744 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.0889. Min Act: -0.1700
Data Index: 6557499 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.0889. Min Act: -0.1700
Data Index: 4513206 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4326. Min Range: -6.4326
Max Act: 6.0576. Min Act: -0.1700
Data Index: 4743261 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19