Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 720 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.4531. Min Act: -0.1700
Data Index: 8094874 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.3906. Min Act: -0.1700
Data Index: 3358755 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.3906. Min Act: -0.1700
Data Index: 3421529 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.3594. Min Act: -0.1700
Data Index: 858691 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.3594. Min Act: -0.1700
Data Index: 7996830 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2969. Min Act: -0.1700
Data Index: 4225696 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2656. Min Act: -0.1700
Data Index: 24595 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2656. Min Act: -0.1700
Data Index: 663182 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2656. Min Act: -0.1700
Data Index: 2104789 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2656. Min Act: -0.1700
Data Index: 2372140 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2656. Min Act: -0.1700
Data Index: 2873967 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2344. Min Act: -0.1700
Data Index: 2855603 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2344. Min Act: -0.1700
Data Index: 4383571 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2031. Min Act: -0.1700
Data Index: 4496604 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2031. Min Act: -0.1700
Data Index: 4678306 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2031. Min Act: -0.1700
Data Index: 8450390 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.2031. Min Act: -0.1700
Data Index: 5851358 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.1719. Min Act: -0.1700
Data Index: 34152 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.1719. Min Act: -0.1700
Data Index: 2264340 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4531. Min Range: -4.4531
Max Act: 4.1719. Min Act: -0.1700
Data Index: 5256028 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19