Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3865 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.6456. Min Act: -0.1700
Data Index: 2022026 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.6456. Min Act: -0.1700
Data Index: 3312437 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.6143. Min Act: -0.1700
Data Index: 790398 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.6143. Min Act: -0.1700
Data Index: 7285558 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.5830. Min Act: -0.1700
Data Index: 2878625 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.5830. Min Act: -0.1700
Data Index: 7044820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.5830. Min Act: -0.1700
Data Index: 3428459 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.5517. Min Act: -0.1700
Data Index: 55629 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.5204. Min Act: -0.1700
Data Index: 6799238 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.5204. Min Act: -0.1700
Data Index: 6974513 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.5204. Min Act: -0.1700
Data Index: 3243170 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 7935612 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 7962743 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 8028114 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 5385608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 3223546 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 6263656 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 8691106 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 6637030 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6456. Min Range: -3.6456
Max Act: 3.4890. Min Act: -0.1700
Data Index: 3089897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19