Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.3874. Min Act: -0.1700
Data Index: 405893 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.3560. Min Act: -0.1700
Data Index: 7580306 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.2461. Min Act: -0.1700
Data Index: 4458872 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1990. Min Act: -0.1700
Data Index: 1846722 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1990. Min Act: -0.1700
Data Index: 7798766 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1990. Min Act: -0.1700
Data Index: 448845 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.2147. Min Act: -0.1700
Data Index: 8663661 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1832. Min Act: -0.1700
Data Index: 573174 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1675. Min Act: -0.1700
Data Index: 2755233 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1832. Min Act: -0.1700
Data Index: 4858960 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1518. Min Act: -0.1700
Data Index: 7705674 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1675. Min Act: -0.1700
Data Index: 6978818 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1675. Min Act: -0.1700
Data Index: 5555330 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1675. Min Act: -0.1700
Data Index: 2312102 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1675. Min Act: -0.1700
Data Index: 6942450 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1675. Min Act: -0.1700
Data Index: 3938284 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1675. Min Act: -0.1700
Data Index: 6657010 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1990. Min Act: -0.1700
Data Index: 6169198 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1203. Min Act: -0.1700
Data Index: 5452437 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3874. Min Range: -3.3874
Max Act: 3.1518. Min Act: -0.1700
Data Index: 2645773 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19