Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.5801. Min Act: -0.1700
Data Index: 5795867 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.4238. Min Act: -0.1700
Data Index: 6870609 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3926. Min Act: -0.1700
Data Index: 2771730 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3926. Min Act: -0.1700
Data Index: 4019687 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3613. Min Act: -0.1700
Data Index: 3066277 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3613. Min Act: -0.1700
Data Index: 5747011 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3613. Min Act: -0.1700
Data Index: 7994057 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 4210250 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2988. Min Act: -0.1700
Data Index: 7591964 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3613. Min Act: -0.1700
Data Index: 889992 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 6152436 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 3773135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2988. Min Act: -0.1700
Data Index: 3366301 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2676. Min Act: -0.1700
Data Index: 4008008 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2988. Min Act: -0.1700
Data Index: 6430922 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2988. Min Act: -0.1700
Data Index: 1133495 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2676. Min Act: -0.1700
Data Index: 226063 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2988. Min Act: -0.1700
Data Index: 2448785 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2988. Min Act: -0.1700
Data Index: 7056289 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 5737124 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19