Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4294. Min Range: -5.4294
Max Act: 5.4294. Min Act: -0.1700
Data Index: 6693789 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4294. Min Range: -5.4294
Max Act: 5.1794. Min Act: -0.1700
Data Index: 6819277 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4294. Min Range: -5.4294
Max Act: 5.0857. Min Act: -0.1700
Data Index: 669678 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4294. Min Range: -5.4294
Max Act: 5.0857. Min Act: -0.1700
Data Index: 6509022 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4294. Min Range: -5.4294
Max Act: 5.0544. Min Act: -0.1700
Data Index: 403229 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4294. Min Range: -5.4294
Max Act: 5.0544. Min Act: -0.1700
Data Index: 4848756 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.9919. Min Act: -0.1700
Data Index: 6819268 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.9294. Min Act: -0.1700
Data Index: 7203540 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.7732. Min Act: -0.1700
Data Index: 6819272 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.8044. Min Act: -0.1700
Data Index: 8345880 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.7419. Min Act: -0.1700
Data Index: 5800710 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.7419. Min Act: -0.1700
Data Index: 4318927 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.7419. Min Act: -0.1700
Data Index: 7203289 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.7107. Min Act: -0.1700
Data Index: 7772862 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.7107. Min Act: -0.1700
Data Index: 1644951 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2591599 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.6794. Min Act: -0.1700
Data Index: 7203539 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.6794. Min Act: -0.1700
Data Index: 2428093 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.6482. Min Act: -0.1700
Data Index: 4967720 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4294. Min Range: -5.4294
Max Act: 4.6482. Min Act: -0.1700
Data Index: 4595100 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19