Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.8871. Min Act: -0.1700
Data Index: 8627789 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.8246. Min Act: -0.1700
Data Index: 2641047 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.8246. Min Act: -0.1700
Data Index: 7964098 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.8246. Min Act: -0.1700
Data Index: 3636776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 5890096 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7621. Min Act: -0.1700
Data Index: 488303 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 6736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 3590270 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 8682626 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7933. Min Act: -0.1700
Data Index: 3730211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7621. Min Act: -0.1700
Data Index: 3616304 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7308. Min Act: -0.1700
Data Index: 5402913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7621. Min Act: -0.1700
Data Index: 390175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7621. Min Act: -0.1700
Data Index: 789449 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7621. Min Act: -0.1700
Data Index: 8605104 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7621. Min Act: -0.1700
Data Index: 8520722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7621. Min Act: -0.1700
Data Index: 7809389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7308. Min Act: -0.1700
Data Index: 5081706 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7308. Min Act: -0.1700
Data Index: 5321101 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8871. Min Range: -4.8871
Max Act: 4.7308. Min Act: -0.1700
Data Index: 1692056 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19