Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.6753. Min Act: -0.1700
Data Index: 4189460 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.6440. Min Act: -0.1700
Data Index: 362922 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.6128. Min Act: -0.1700
Data Index: 7570669 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.5815. Min Act: -0.1700
Data Index: 11203 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.4878. Min Act: -0.1700
Data Index: 6175584 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.4878. Min Act: -0.1700
Data Index: 4610759 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.4878. Min Act: -0.1700
Data Index: 4610758 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.4878. Min Act: -0.1700
Data Index: 4159861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.4565. Min Act: -0.1700
Data Index: 2409974 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.4878. Min Act: -0.1700
Data Index: 6826442 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.4253. Min Act: -0.1700
Data Index: 2380269 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.3940. Min Act: -0.1700
Data Index: 1255471 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.3628. Min Act: -0.1700
Data Index: 6838724 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.3628. Min Act: -0.1700
Data Index: 6199964 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.3315. Min Act: -0.1700
Data Index: 364794 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.3003. Min Act: -0.1700
Data Index: 5582992 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.2690. Min Act: -0.1700
Data Index: 2426988 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.2377. Min Act: -0.1700
Data Index: 5037631 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.2065. Min Act: -0.1700
Data Index: 5037616 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6753. Min Range: -4.6753
Max Act: 4.2377. Min Act: -0.1700
Data Index: 5985241 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19