Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5673. Min Act: -0.1700
Data Index: 4744522 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5673. Min Act: -0.1700
Data Index: 2507305 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5673. Min Act: -0.1700
Data Index: 4300730 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5673. Min Act: -0.1700
Data Index: 7454080 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5360. Min Act: -0.1700
Data Index: 5961853 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5360. Min Act: -0.1700
Data Index: 8554408 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5360. Min Act: -0.1700
Data Index: 3205932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5360. Min Act: -0.1700
Data Index: 6698965 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5047. Min Act: -0.1700
Data Index: 7111666 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5047. Min Act: -0.1700
Data Index: 238177 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5047. Min Act: -0.1700
Data Index: 7800158 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.5047. Min Act: -0.1700
Data Index: 5645273 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.4734. Min Act: -0.1700
Data Index: 1668763 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.4734. Min Act: -0.1700
Data Index: 4506402 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.4734. Min Act: -0.1700
Data Index: 4878299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.4734. Min Act: -0.1700
Data Index: 2914999 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.4734. Min Act: -0.1700
Data Index: 5123055 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.4734. Min Act: -0.1700
Data Index: 5144460 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.4734. Min Act: -0.1700
Data Index: 2134028 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5673. Min Range: -3.5673
Max Act: 3.4734. Min Act: -0.1700
Data Index: 2142398 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19