Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.4534. Min Act: -0.1700
Data Index: 846566 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.2033. Min Act: -0.1700
Data Index: 2375852 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.2033. Min Act: -0.1700
Data Index: 995722 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1721. Min Act: -0.1700
Data Index: 7295298 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.1096. Min Act: -0.1700
Data Index: 629641 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0783. Min Act: -0.1700
Data Index: 5365675 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0783. Min Act: -0.1700
Data Index: 1383844 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0783. Min Act: -0.1700
Data Index: 8465089 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0783. Min Act: -0.1700
Data Index: 6948398 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0471. Min Act: -0.1700
Data Index: 1573227 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0471. Min Act: -0.1700
Data Index: 8051012 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0158. Min Act: -0.1700
Data Index: 1036292 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0783. Min Act: -0.1700
Data Index: 6686785 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0158. Min Act: -0.1700
Data Index: 4448861 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0158. Min Act: -0.1700
Data Index: 6097113 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4534. Min Range: -4.4534
Max Act: 3.9845. Min Act: -0.1700
Data Index: 8686400 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4534. Min Range: -4.4534
Max Act: 4.0158. Min Act: -0.1700
Data Index: 8686401 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4534. Min Range: -4.4534
Max Act: 3.9533. Min Act: -0.1700
Data Index: 1077078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4534. Min Range: -4.4534
Max Act: 3.9533. Min Act: -0.1700
Data Index: 1428665 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4534. Min Range: -4.4534
Max Act: 3.9220. Min Act: -0.1700
Data Index: 2393576 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19