Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5532 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.5335. Min Act: -0.1700
Data Index: 7012222 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.4085. Min Act: -0.1700
Data Index: 2056497 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.1585. Min Act: -0.1700
Data Index: 86060 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.1272. Min Act: -0.1700
Data Index: 8208122 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.1585. Min Act: -0.1700
Data Index: 894595 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.1272. Min Act: -0.1700
Data Index: 3281258 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.0647. Min Act: -0.1700
Data Index: 1391406 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.1272. Min Act: -0.1700
Data Index: 2698389 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.0960. Min Act: -0.1700
Data Index: 8498073 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.0647. Min Act: -0.1700
Data Index: 7068124 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.0960. Min Act: -0.1700
Data Index: 2956602 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.0335. Min Act: -0.1700
Data Index: 6559223 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.0335. Min Act: -0.1700
Data Index: 3370273 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5335. Min Range: -7.5335
Max Act: 7.0022. Min Act: -0.1700
Data Index: 1969154 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5335. Min Range: -7.5335
Max Act: 6.9710. Min Act: -0.1700
Data Index: 3077167 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5335. Min Range: -7.5335
Max Act: 6.9710. Min Act: -0.1700
Data Index: 1586664 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5335. Min Range: -7.5335
Max Act: 6.9710. Min Act: -0.1700
Data Index: 1844680 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5335. Min Range: -7.5335
Max Act: 6.9710. Min Act: -0.1700
Data Index: 556049 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5335. Min Range: -7.5335
Max Act: 6.9397. Min Act: -0.1700
Data Index: 4484391 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5335. Min Range: -7.5335
Max Act: 6.9085. Min Act: -0.1700
Data Index: 2945097 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19