Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.4078. Min Act: -0.1700
Data Index: 2901837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.3453. Min Act: -0.1700
Data Index: 1620288 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.3453. Min Act: -0.1700
Data Index: 5810170 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.3140. Min Act: -0.1700
Data Index: 2337005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.3140. Min Act: -0.1700
Data Index: 1956557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.3140. Min Act: -0.1700
Data Index: 253832 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.3140. Min Act: -0.1700
Data Index: 6508154 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.3140. Min Act: -0.1700
Data Index: 749350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2828. Min Act: -0.1700
Data Index: 5890230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2828. Min Act: -0.1700
Data Index: 6150323 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2828. Min Act: -0.1700
Data Index: 1081081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2828. Min Act: -0.1700
Data Index: 776857 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2828. Min Act: -0.1700
Data Index: 6774799 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2828. Min Act: -0.1700
Data Index: 143276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2828. Min Act: -0.1700
Data Index: 2363005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2828. Min Act: -0.1700
Data Index: 6758519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2515. Min Act: -0.1700
Data Index: 270460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2515. Min Act: -0.1700
Data Index: 5996930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2515. Min Act: -0.1700
Data Index: 2265692 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4078. Min Range: -4.4078
Max Act: 4.2515. Min Act: -0.1700
Data Index: 2279429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19