Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3947 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.8515. Min Act: -0.1700
Data Index: 8526031 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.6640. Min Act: -0.1700
Data Index: 2934260 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.6640. Min Act: -0.1700
Data Index: 5983891 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.6327. Min Act: -0.1700
Data Index: 6930297 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.5702. Min Act: -0.1700
Data Index: 8035156 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.5077. Min Act: -0.1700
Data Index: 62685 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.4765. Min Act: -0.1700
Data Index: 1086266 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.4452. Min Act: -0.1700
Data Index: 4097800 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.4140. Min Act: -0.1700
Data Index: 3797479 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.4140. Min Act: -0.1700
Data Index: 4462570 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.4140. Min Act: -0.1700
Data Index: 4356451 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.3827. Min Act: -0.1700
Data Index: 1069281 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.4140. Min Act: -0.1700
Data Index: 6713138 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.3827. Min Act: -0.1700
Data Index: 1041578 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.3827. Min Act: -0.1700
Data Index: 2323639 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.4140. Min Act: -0.1700
Data Index: 5845950 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.3827. Min Act: -0.1700
Data Index: 7828815 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.3515. Min Act: -0.1700
Data Index: 6320440 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.3827. Min Act: -0.1700
Data Index: 679265 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8515. Min Range: -5.8515
Max Act: 5.3515. Min Act: -0.1700
Data Index: 7187650 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19