Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6162. Min Range: -8.6162
Max Act: 8.6162. Min Act: -0.1700
Data Index: 7701777 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6162. Min Range: -8.6162
Max Act: 8.3037. Min Act: -0.1700
Data Index: 5605305 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6162. Min Range: -8.6162
Max Act: 8.0537. Min Act: -0.1700
Data Index: 398202 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.9600. Min Act: -0.1700
Data Index: 1558132 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.9287. Min Act: -0.1700
Data Index: 8690745 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.9287. Min Act: -0.1700
Data Index: 6699156 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.8662. Min Act: -0.1700
Data Index: 2127642 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.8662. Min Act: -0.1700
Data Index: 3728012 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.8037. Min Act: -0.1700
Data Index: 1802362 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.7725. Min Act: -0.1700
Data Index: 5571135 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.7725. Min Act: -0.1700
Data Index: 8766168 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.7412. Min Act: -0.1700
Data Index: 806906 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.6787. Min Act: -0.1700
Data Index: 3587307 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.6787. Min Act: -0.1700
Data Index: 7531993 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.6475. Min Act: -0.1700
Data Index: 5075679 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.6475. Min Act: -0.1700
Data Index: 8701461 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.5850. Min Act: -0.1700
Data Index: 2228585 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.5850. Min Act: -0.1700
Data Index: 3514165 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.5537. Min Act: -0.1700
Data Index: 6687889 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6162. Min Range: -8.6162
Max Act: 7.5225. Min Act: -0.1700
Data Index: 2681470 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19