Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2383. Min Range: -5.2383
Max Act: 5.2071. Min Act: -0.1700
Data Index: 8002996 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2383. Min Range: -5.2383
Max Act: 5.2383. Min Act: -0.1700
Data Index: 3590944 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2383. Min Range: -5.2383
Max Act: 5.1133. Min Act: -0.1700
Data Index: 1747878 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2383. Min Range: -5.2383
Max Act: 5.0508. Min Act: -0.1700
Data Index: 788223 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.9883. Min Act: -0.1700
Data Index: 4691040 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2383. Min Range: -5.2383
Max Act: 5.0196. Min Act: -0.1700
Data Index: 2305334 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.9571. Min Act: -0.1700
Data Index: 5081204 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.9571. Min Act: -0.1700
Data Index: 340997 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.9258. Min Act: -0.1700
Data Index: 3087509 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.9571. Min Act: -0.1700
Data Index: 5380758 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.8946. Min Act: -0.1700
Data Index: 1907786 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.8946. Min Act: -0.1700
Data Index: 6164014 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.8633. Min Act: -0.1700
Data Index: 1296271 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.8321. Min Act: -0.1700
Data Index: 2934502 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.8008. Min Act: -0.1700
Data Index: 7412914 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.6758. Min Act: -0.1700
Data Index: 3747673 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.7071. Min Act: -0.1700
Data Index: 6274413 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.7071. Min Act: -0.1700
Data Index: 4169538 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.7071. Min Act: -0.1700
Data Index: 3325889 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2383. Min Range: -5.2383
Max Act: 4.6758. Min Act: -0.1700
Data Index: 5405863 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19