Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2243 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5656. Min Act: -0.1700
Data Index: 6722850 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5656. Min Act: -0.1700
Data Index: 2187590 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5656. Min Act: -0.1700
Data Index: 1176087 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5656. Min Act: -0.1700
Data Index: 7613909 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5656. Min Act: -0.1700
Data Index: 553415 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 1584171 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 4049467 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 3134811 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 1180681 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 8741673 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 7697542 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 7686132 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 7316536 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 6889882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5343. Min Act: -0.1700
Data Index: 16664 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5031. Min Act: -0.1700
Data Index: 3360790 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5031. Min Act: -0.1700
Data Index: 3580741 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5031. Min Act: -0.1700
Data Index: 3660661 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5031. Min Act: -0.1700
Data Index: 691952 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5656. Min Range: -5.5656
Max Act: 5.5031. Min Act: -0.1700
Data Index: 4359481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19