Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3307 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.9482. Min Act: -0.1700
Data Index: 5587896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.9482. Min Act: -0.1700
Data Index: 313172 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.9482. Min Act: -0.1700
Data Index: 6514615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.9482. Min Act: -0.1700
Data Index: 4954192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.9482. Min Act: -0.1700
Data Index: 2294869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6669. Min Act: -0.1700
Data Index: 7773532 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6669. Min Act: -0.1700
Data Index: 3095083 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6044. Min Act: -0.1700
Data Index: 4724409 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.5732. Min Act: -0.1700
Data Index: 5995136 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.5732. Min Act: -0.1700
Data Index: 137529 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.5732. Min Act: -0.1700
Data Index: 7821135 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.5107. Min Act: -0.1700
Data Index: 253304 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.5107. Min Act: -0.1700
Data Index: 7424632 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.4794. Min Act: -0.1700
Data Index: 497023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.4794. Min Act: -0.1700
Data Index: 4898204 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.4482. Min Act: -0.1700
Data Index: 3036341 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.4169. Min Act: -0.1700
Data Index: 8066345 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.4169. Min Act: -0.1700
Data Index: 5668974 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.4169. Min Act: -0.1700
Data Index: 2707277 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.3857. Min Act: -0.1700
Data Index: 2945422 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19