Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 507 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3211. Min Range: -6.3211
Max Act: 6.3211. Min Act: -0.1700
Data Index: 2370035 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3211. Min Range: -6.3211
Max Act: 6.1648. Min Act: -0.1700
Data Index: 6260138 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3211. Min Range: -6.3211
Max Act: 6.1023. Min Act: -0.1700
Data Index: 5887471 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.8836. Min Act: -0.1700
Data Index: 970646 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.9773. Min Act: -0.1700
Data Index: 360374 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.9461. Min Act: -0.1700
Data Index: 7232517 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.7586. Min Act: -0.1700
Data Index: 1521179 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.8211. Min Act: -0.1700
Data Index: 7192239 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.8211. Min Act: -0.1700
Data Index: 6234417 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6648. Min Act: -0.1700
Data Index: 3240029 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6023. Min Act: -0.1700
Data Index: 6050335 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6648. Min Act: -0.1696
Data Index: 2329453 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6336. Min Act: -0.1700
Data Index: 8383087 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6336. Min Act: -0.1700
Data Index: 3942804 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6961. Min Act: -0.1700
Data Index: 4502618 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6648. Min Act: -0.1700
Data Index: 2327266 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6023. Min Act: -0.1700
Data Index: 550360 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6336. Min Act: -0.1700
Data Index: 4658053 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.6336. Min Act: -0.1700
Data Index: 2206308 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3211. Min Range: -6.3211
Max Act: 5.5398. Min Act: -0.1700
Data Index: 2806896 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19