Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1269 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.8347. Min Act: -0.1700
Data Index: 2008882 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.7722. Min Act: -0.1700
Data Index: 3843254 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.6472. Min Act: -0.1700
Data Index: 673433 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.6160. Min Act: -0.1700
Data Index: 2359465 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.5847. Min Act: -0.1700
Data Index: 1956437 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.5535. Min Act: -0.1700
Data Index: 631126 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.5535. Min Act: -0.1700
Data Index: 1211327 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.5535. Min Act: -0.1700
Data Index: 4455397 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.5535. Min Act: -0.1700
Data Index: 168708 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4910. Min Act: -0.1700
Data Index: 8748365 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4910. Min Act: -0.1700
Data Index: 8484933 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4910. Min Act: -0.1700
Data Index: 4967468 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4597. Min Act: -0.1700
Data Index: 4661175 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4910. Min Act: -0.1700
Data Index: 5642306 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4597. Min Act: -0.1700
Data Index: 5814424 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4597. Min Act: -0.1700
Data Index: 6548922 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4910. Min Act: -0.1700
Data Index: 518901 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4910. Min Act: -0.1700
Data Index: 7024272 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4597. Min Act: -0.1700
Data Index: 3627731 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8347. Min Range: -4.8347
Max Act: 4.4285. Min Act: -0.1700
Data Index: 3678308 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19