Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4336 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0134. Min Range: -4.0134
Max Act: 4.0134. Min Act: -0.1700
Data Index: 7510402 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.9196. Min Act: -0.1700
Data Index: 3175187 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.8883. Min Act: -0.1700
Data Index: 1726421 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.8258. Min Act: -0.1700
Data Index: 6233523 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.7632. Min Act: -0.1700
Data Index: 7521715 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.7007. Min Act: -0.1700
Data Index: 8570221 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.6381. Min Act: -0.1700
Data Index: 6633386 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.6068. Min Act: -0.1700
Data Index: 3917821 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.6381. Min Act: -0.1700
Data Index: 3509848 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.5755. Min Act: -0.1700
Data Index: 6739859 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.5755. Min Act: -0.1700
Data Index: 3697602 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.5755. Min Act: -0.1700
Data Index: 7053273 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.5442. Min Act: -0.1700
Data Index: 1060797 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.5128. Min Act: -0.1700
Data Index: 4826333 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.5128. Min Act: -0.1700
Data Index: 2047092 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.5128. Min Act: -0.1700
Data Index: 3369979 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.5128. Min Act: -0.1700
Data Index: 2671127 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.4815. Min Act: -0.1700
Data Index: 7316553 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.4815. Min Act: -0.1700
Data Index: 2215739 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0134. Min Range: -4.0134
Max Act: 3.4815. Min Act: -0.1700
Data Index: 5131812 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19