Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5210 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.6135. Min Act: -0.1700
Data Index: 3951503 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.4573. Min Act: -0.1700
Data Index: 4420393 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.3323. Min Act: -0.1700
Data Index: 1305884 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.3635. Min Act: -0.1700
Data Index: 3346406 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.3010. Min Act: -0.1700
Data Index: 15539 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.2698. Min Act: -0.1700
Data Index: 7835971 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.2698. Min Act: -0.1700
Data Index: 8306331 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.2073. Min Act: -0.1700
Data Index: 5448450 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1760. Min Act: -0.1700
Data Index: 446758 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.2073. Min Act: -0.1700
Data Index: 6127470 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1760. Min Act: -0.1700
Data Index: 1386355 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1760. Min Act: -0.1700
Data Index: 6252475 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1448. Min Act: -0.1700
Data Index: 3182325 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1448. Min Act: -0.1700
Data Index: 7574430 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1135. Min Act: -0.1700
Data Index: 5348316 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1448. Min Act: -0.1700
Data Index: 8276277 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1135. Min Act: -0.1700
Data Index: 6447231 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1135. Min Act: -0.1700
Data Index: 4897268 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1135. Min Act: -0.1700
Data Index: 2953330 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6135. Min Range: -5.6135
Max Act: 5.1135. Min Act: -0.1700
Data Index: 7996591 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19