Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.8575. Min Act: -0.1700
Data Index: 4800417 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.8575. Min Act: -0.1700
Data Index: 6305258 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.8262. Min Act: -0.1700
Data Index: 441560 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.7950. Min Act: -0.1700
Data Index: 4163028 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.7637. Min Act: -0.1700
Data Index: 6305261 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.7325. Min Act: -0.1700
Data Index: 2790318 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.7325. Min Act: -0.1700
Data Index: 1690218 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.7012. Min Act: -0.1700
Data Index: 5860694 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.7012. Min Act: -0.1700
Data Index: 6344385 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6700. Min Act: -0.1700
Data Index: 46762 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6700. Min Act: -0.1700
Data Index: 6300817 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6700. Min Act: -0.1700
Data Index: 8064603 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6700. Min Act: -0.1700
Data Index: 6305259 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6387. Min Act: -0.1700
Data Index: 6344384 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6700. Min Act: -0.1700
Data Index: 2412295 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6387. Min Act: -0.1700
Data Index: 6479854 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6387. Min Act: -0.1700
Data Index: 6305257 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6075. Min Act: -0.1700
Data Index: 2654859 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6700. Min Act: -0.1700
Data Index: 2790314 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8575. Min Range: -4.8575
Max Act: 4.6700. Min Act: -0.1700
Data Index: 3392052 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19