Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4058. Min Range: -7.4058
Max Act: 7.4058. Min Act: -0.1700
Data Index: 3867264 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4058. Min Range: -7.4058
Max Act: 7.2808. Min Act: -0.1700
Data Index: 3257703 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4058. Min Range: -7.4058
Max Act: 7.2808. Min Act: -0.1700
Data Index: 5575118 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4058. Min Range: -7.4058
Max Act: 7.0933. Min Act: -0.1700
Data Index: 2115082 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.9996. Min Act: -0.1700
Data Index: 6531895 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.9371. Min Act: -0.1700
Data Index: 2576433 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.8746. Min Act: -0.1700
Data Index: 3413803 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.8433. Min Act: -0.1700
Data Index: 873537 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.7496. Min Act: -0.1700
Data Index: 455030 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.7808. Min Act: -0.1700
Data Index: 2722049 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.7183. Min Act: -0.1700
Data Index: 8145313 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.7496. Min Act: -0.1700
Data Index: 4151487 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.6558. Min Act: -0.1700
Data Index: 5420111 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.6558. Min Act: -0.1700
Data Index: 245523 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.6558. Min Act: -0.1700
Data Index: 5624375 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.6246. Min Act: -0.1700
Data Index: 6993021 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.5621. Min Act: -0.1700
Data Index: 120959 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.5308. Min Act: -0.1700
Data Index: 8029912 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.5308. Min Act: -0.1700
Data Index: 5571156 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4058. Min Range: -7.4058
Max Act: 6.5308. Min Act: -0.1700
Data Index: 6549452 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19