Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 325 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.5097. Min Act: -0.1700
Data Index: 5656816 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.5097. Min Act: -0.1700
Data Index: 2392355 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.4472. Min Act: -0.1700
Data Index: 2441416 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.3222. Min Act: -0.1700
Data Index: 6819939 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.1972. Min Act: -0.1700
Data Index: 6253343 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.2597. Min Act: -0.1700
Data Index: 7914180 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.1972. Min Act: -0.1700
Data Index: 8039279 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.1972. Min Act: -0.1700
Data Index: 4677034 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.1972. Min Act: -0.1700
Data Index: 8656450 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.1972. Min Act: -0.1700
Data Index: 8180212 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.1347. Min Act: -0.1700
Data Index: 2112739 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.1347. Min Act: -0.1700
Data Index: 2009891 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.0722. Min Act: -0.1700
Data Index: 3777363 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.0097. Min Act: -0.1700
Data Index: 1011354 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5097. Min Range: -8.5097
Max Act: 7.9472. Min Act: -0.1700
Data Index: 8348213 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5097. Min Range: -8.5097
Max Act: 7.9472. Min Act: -0.1700
Data Index: 21682 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5097. Min Range: -8.5097
Max Act: 8.0097. Min Act: -0.1700
Data Index: 3423258 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5097. Min Range: -8.5097
Max Act: 7.9472. Min Act: -0.1700
Data Index: 6236231 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5097. Min Range: -8.5097
Max Act: 7.9472. Min Act: -0.1700
Data Index: 8820471 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5097. Min Range: -8.5097
Max Act: 7.8847. Min Act: -0.1700
Data Index: 1251470 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19