Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 362 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7905. Min Range: -8.7905
Max Act: 8.7905. Min Act: -0.1700
Data Index: 4473426 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7905. Min Range: -8.7905
Max Act: 8.6030. Min Act: -0.1700
Data Index: 2028361 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7905. Min Range: -8.7905
Max Act: 8.3530. Min Act: -0.1700
Data Index: 1216750 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7905. Min Range: -8.7905
Max Act: 8.2905. Min Act: -0.1700
Data Index: 143863 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7905. Min Range: -8.7905
Max Act: 8.3530. Min Act: -0.1700
Data Index: 6363217 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7905. Min Range: -8.7905
Max Act: 8.0092. Min Act: -0.1700
Data Index: 8369722 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.9155. Min Act: -0.1700
Data Index: 1306360 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.8217. Min Act: -0.1700
Data Index: 1216754 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.7592. Min Act: -0.1700
Data Index: 316249 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 3000741 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 5005173 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.6967. Min Act: -0.1700
Data Index: 4890291 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.6342. Min Act: -0.1700
Data Index: 4890292 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.6967. Min Act: -0.1700
Data Index: 8134389 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.6342. Min Act: -0.1700
Data Index: 8713278 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.6342. Min Act: -0.1700
Data Index: 3942649 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.6655. Min Act: -0.1700
Data Index: 959395 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.6655. Min Act: -0.1700
Data Index: 3557274 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.6342. Min Act: -0.1700
Data Index: 6866862 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7905. Min Range: -8.7905
Max Act: 7.5405. Min Act: -0.1700
Data Index: 3374110 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19