Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6154. Min Range: -5.6154
Max Act: 5.6154. Min Act: -0.1700
Data Index: 1600066 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6154. Min Range: -5.6154
Max Act: 5.4592. Min Act: -0.1700
Data Index: 79114 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6154. Min Range: -5.6154
Max Act: 5.3654. Min Act: -0.1700
Data Index: 1600076 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6154. Min Range: -5.6154
Max Act: 5.3342. Min Act: -0.1700
Data Index: 127632 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6154. Min Range: -5.6154
Max Act: 5.1779. Min Act: -0.1700
Data Index: 843385 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6154. Min Range: -5.6154
Max Act: 5.1779. Min Act: -0.1700
Data Index: 6170432 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6154. Min Range: -5.6154
Max Act: 5.0529. Min Act: -0.1700
Data Index: 1493176 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6154. Min Range: -5.6154
Max Act: 5.0217. Min Act: -0.1700
Data Index: 500775 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.9904. Min Act: -0.1700
Data Index: 3051667 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.9592. Min Act: -0.1700
Data Index: 7573881 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.9592. Min Act: -0.1700
Data Index: 6344745 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.9592. Min Act: -0.1700
Data Index: 6459865 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.9279. Min Act: -0.1700
Data Index: 8012801 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.9279. Min Act: -0.1700
Data Index: 6022542 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.9279. Min Act: -0.1700
Data Index: 3224353 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.8967. Min Act: -0.1700
Data Index: 6476381 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.8654. Min Act: -0.1700
Data Index: 2263505 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.8654. Min Act: -0.1700
Data Index: 2700625 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.8654. Min Act: -0.1700
Data Index: 7456982 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6154. Min Range: -5.6154
Max Act: 4.8654. Min Act: -0.1700
Data Index: 2772506 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19