Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4303 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.7653. Min Act: -0.1700
Data Index: 7008279 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.5778. Min Act: -0.1700
Data Index: 3228889 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.5153. Min Act: -0.1700
Data Index: 8353013 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.4528. Min Act: -0.1700
Data Index: 1753475 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.4528. Min Act: -0.1700
Data Index: 2913595 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.4215. Min Act: -0.1700
Data Index: 5763287 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.3903. Min Act: -0.1700
Data Index: 1610776 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.3903. Min Act: -0.1700
Data Index: 1388975 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.3590. Min Act: -0.1700
Data Index: 97490 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.3278. Min Act: -0.1700
Data Index: 587205 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.3278. Min Act: -0.1700
Data Index: 1261964 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2340. Min Act: -0.1699
Data Index: 696459 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2653. Min Act: -0.1700
Data Index: 2864842 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2340. Min Act: -0.1700
Data Index: 5782341 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2653. Min Act: -0.1700
Data Index: 2666003 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2340. Min Act: -0.1700
Data Index: 4961266 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2340. Min Act: -0.1700
Data Index: 5165018 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2340. Min Act: -0.1700
Data Index: 1641833 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2340. Min Act: -0.1700
Data Index: 583408 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7653. Min Range: -5.7653
Max Act: 5.2340. Min Act: -0.1700
Data Index: 1348717 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19