Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4494 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.8519. Min Act: -0.1700
Data Index: 2499473 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.7269. Min Act: -0.1700
Data Index: 6915606 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.4144. Min Act: -0.1700
Data Index: 6759744 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.1019. Min Act: -0.1700
Data Index: 6107393 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.0394. Min Act: -0.1700
Data Index: 574263 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.0394. Min Act: -0.1700
Data Index: 692846 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.0394. Min Act: -0.1700
Data Index: 4031944 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.0394. Min Act: -0.1700
Data Index: 4017273 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8519. Min Range: -7.8519
Max Act: 7.0394. Min Act: -0.1700
Data Index: 2990381 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.8831. Min Act: -0.1700
Data Index: 6872772 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.9456. Min Act: -0.1700
Data Index: 6238729 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.9144. Min Act: -0.1700
Data Index: 2257297 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.8519. Min Act: -0.1700
Data Index: 2685263 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.8831. Min Act: -0.1700
Data Index: 566040 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.9144. Min Act: -0.1700
Data Index: 1028216 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.8831. Min Act: -0.1700
Data Index: 6162945 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.8206. Min Act: -0.1700
Data Index: 698490 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.7581. Min Act: -0.1700
Data Index: 5634827 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.7894. Min Act: -0.1700
Data Index: 6404065 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8519. Min Range: -7.8519
Max Act: 6.7894. Min Act: -0.1700
Data Index: 3655861 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19