Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2695 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.3614. Min Act: -0.1700
Data Index: 5715014 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.3301. Min Act: -0.1700
Data Index: 5678778 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.2676. Min Act: -0.1700
Data Index: 4284648 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.2989. Min Act: -0.1700
Data Index: 8254812 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3614. Min Range: -7.3614
Max Act: 5.5489. Min Act: -0.1700
Data Index: 119936 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.2676. Min Act: -0.1700
Data Index: 8155544 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.2676. Min Act: -0.1700
Data Index: 8528560 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.1739. Min Act: -0.1700
Data Index: 4550741 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.1426. Min Act: -0.1700
Data Index: 7985573 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.2676. Min Act: -0.1700
Data Index: 563331 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.2051. Min Act: -0.1700
Data Index: 8467191 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.1739. Min Act: -0.1700
Data Index: 4433803 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.2364. Min Act: -0.1700
Data Index: 215194 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.1114. Min Act: -0.1700
Data Index: 7991885 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.2051. Min Act: -0.1700
Data Index: 4991130 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.1426. Min Act: -0.1700
Data Index: 6985181 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.1426. Min Act: -0.1700
Data Index: 4268468 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.1426. Min Act: -0.1700
Data Index: 7272278 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.0801. Min Act: -0.1700
Data Index: 7027250 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3614. Min Range: -7.3614
Max Act: 7.1426. Min Act: -0.1700
Data Index: 2053259 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19