Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1593 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4357. Min Act: -0.1700
Data Index: 4725147 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4045. Min Act: -0.1700
Data Index: 7279313 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4045. Min Act: -0.1700
Data Index: 886295 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3732. Min Act: -0.1700
Data Index: 6387036 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.4045. Min Act: -0.1700
Data Index: 6294820 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3420. Min Act: -0.1700
Data Index: 5215550 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3107. Min Act: -0.1700
Data Index: 5354134 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3107. Min Act: -0.1700
Data Index: 1611160 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2795. Min Act: -0.1700
Data Index: 1820422 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2795. Min Act: -0.1700
Data Index: 8117113 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.3107. Min Act: -0.1700
Data Index: 7028152 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2795. Min Act: -0.1700
Data Index: 4287162 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2795. Min Act: -0.1700
Data Index: 7503348 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2795. Min Act: -0.1700
Data Index: 6648361 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2795. Min Act: -0.1700
Data Index: 6606924 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 276409 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 8063967 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2795. Min Act: -0.1700
Data Index: 1552351 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 6867090 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4357. Min Range: -5.4357
Max Act: 5.2482. Min Act: -0.1700
Data Index: 8696919 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19