Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.4699. Min Act: -0.1700
Data Index: 4499374 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.4523. Min Act: -0.1700
Data Index: 8056749 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3995. Min Act: -0.1700
Data Index: 7423079 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3819. Min Act: -0.1700
Data Index: 6153052 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3819. Min Act: -0.1700
Data Index: 4090765 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3642. Min Act: -0.1700
Data Index: 185280 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3642. Min Act: -0.1700
Data Index: 5439554 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3466. Min Act: -0.1700
Data Index: 5328417 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3642. Min Act: -0.1700
Data Index: 1816780 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3290. Min Act: -0.1700
Data Index: 6572836 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3290. Min Act: -0.1700
Data Index: 2960333 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1700
Data Index: 1591653 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1700
Data Index: 7847061 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1700
Data Index: 5966410 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1700
Data Index: 7818852 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1700
Data Index: 7713998 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1699
Data Index: 4194159 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1700
Data Index: 7501821 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1700
Data Index: 224507 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4699. Min Range: -1.4699
Max Act: 1.3113. Min Act: -0.1700
Data Index: 6241492 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19