Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0932. Min Range: -5.0932
Max Act: 5.0932. Min Act: -0.1700
Data Index: 6028527 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9995. Min Act: -0.1700
Data Index: 8573013 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9370. Min Act: -0.1700
Data Index: 8227938 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9057. Min Act: -0.1700
Data Index: 1310801 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9057. Min Act: -0.1700
Data Index: 7819696 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9370. Min Act: -0.1700
Data Index: 551337 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.9057. Min Act: -0.1700
Data Index: 758362 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8745. Min Act: -0.1700
Data Index: 7124268 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8432. Min Act: -0.1700
Data Index: 668547 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8432. Min Act: -0.1700
Data Index: 6986825 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8432. Min Act: -0.1700
Data Index: 636419 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8745. Min Act: -0.1700
Data Index: 5556524 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8120. Min Act: -0.1700
Data Index: 5549726 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8432. Min Act: -0.1700
Data Index: 1015701 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8432. Min Act: -0.1700
Data Index: 4402186 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8432. Min Act: -0.1700
Data Index: 3555670 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8432. Min Act: -0.1700
Data Index: 3440368 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8120. Min Act: -0.1700
Data Index: 4927828 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8120. Min Act: -0.1700
Data Index: 4482187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0932. Min Range: -5.0932
Max Act: 4.8120. Min Act: -0.1700
Data Index: 2878818 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19