Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.3622. Min Act: -0.1700
Data Index: 4120347 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.2837. Min Act: -0.1700
Data Index: 8783374 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1737. Min Act: -0.1700
Data Index: 1352066 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1737. Min Act: -0.1700
Data Index: 2014048 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1580. Min Act: -0.1700
Data Index: 7498635 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1580. Min Act: -0.1700
Data Index: 2846838 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1580. Min Act: -0.1700
Data Index: 3932209 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1422. Min Act: -0.1700
Data Index: 727068 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1265. Min Act: -0.1700
Data Index: 6642292 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1580. Min Act: -0.1700
Data Index: 7824187 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1265. Min Act: -0.1700
Data Index: 3466621 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1265. Min Act: -0.1700
Data Index: 6519861 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1265. Min Act: -0.1700
Data Index: 571711 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1265. Min Act: -0.1700
Data Index: 715170 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1265. Min Act: -0.1700
Data Index: 2272847 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.0792. Min Act: -0.1700
Data Index: 7642611 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.1107. Min Act: -0.1700
Data Index: 4195156 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.0950. Min Act: -0.1700
Data Index: 7204060 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.0950. Min Act: -0.1700
Data Index: 6322899 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3622. Min Range: -3.3622
Max Act: 3.0792. Min Act: -0.1700
Data Index: 6875233 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19