Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 266 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5318. Min Act: -0.1700
Data Index: 3357213 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5318. Min Act: -0.1700
Data Index: 7652558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5318. Min Act: -0.1700
Data Index: 1664383 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 5885265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.4692. Min Act: -0.1700
Data Index: 5178852 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 5042138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 3897549 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 3882922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 3664562 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 911129 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 878843 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 8539431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 2922520 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 1261298 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.5005. Min Act: -0.1700
Data Index: 5837780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.4692. Min Act: -0.1700
Data Index: 35017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.4692. Min Act: -0.1700
Data Index: 2048481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.4692. Min Act: -0.1700
Data Index: 2098223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.4692. Min Act: -0.1700
Data Index: 5219811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5318. Min Range: -3.5318
Max Act: 3.4692. Min Act: -0.1700
Data Index: 5313227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19