Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1403. Min Range: -4.1403
Max Act: 4.1403. Min Act: -0.1700
Data Index: 185366 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1403. Min Range: -4.1403
Max Act: 4.0778. Min Act: -0.1700
Data Index: 8796989 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1403. Min Range: -4.1403
Max Act: 4.0465. Min Act: -0.1700
Data Index: 6022248 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1403. Min Range: -4.1403
Max Act: 4.0153. Min Act: -0.1700
Data Index: 2881982 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.9840. Min Act: -0.1700
Data Index: 7934264 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.9528. Min Act: -0.1700
Data Index: 3969556 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.9528. Min Act: -0.1700
Data Index: 7287385 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.8590. Min Act: -0.1700
Data Index: 6040155 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.8590. Min Act: -0.1700
Data Index: 4058915 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.8590. Min Act: -0.1700
Data Index: 6596201 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.8277. Min Act: -0.1700
Data Index: 4556123 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.7964. Min Act: -0.1700
Data Index: 735589 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.8277. Min Act: -0.1700
Data Index: 1612457 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.8590. Min Act: -0.1700
Data Index: 4944697 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.7964. Min Act: -0.1700
Data Index: 5024611 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.7651. Min Act: -0.1700
Data Index: 843909 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.7651. Min Act: -0.1700
Data Index: 2968686 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.7651. Min Act: -0.1700
Data Index: 7470762 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.7651. Min Act: -0.1700
Data Index: 3581018 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1403. Min Range: -4.1403
Max Act: 3.7339. Min Act: -0.1700
Data Index: 373612 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19