Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3852 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.9113. Min Act: -0.1700
Data Index: 7365447 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7863. Min Act: -0.1700
Data Index: 5860223 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.7238. Min Act: -0.1700
Data Index: 1968223 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5988. Min Act: -0.1700
Data Index: 717226 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5676. Min Act: -0.1700
Data Index: 1278286 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5051. Min Act: -0.1700
Data Index: 1439489 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5051. Min Act: -0.1700
Data Index: 522072 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4738. Min Act: -0.1700
Data Index: 7033451 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4738. Min Act: -0.1697
Data Index: 473121 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.5051. Min Act: -0.1700
Data Index: 3142907 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4426. Min Act: -0.1700
Data Index: 7252945 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4426. Min Act: -0.1699
Data Index: 6614526 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4426. Min Act: -0.1700
Data Index: 2746276 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4426. Min Act: -0.1700
Data Index: 4382579 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 3749639 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 6285905 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 69427 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 3618729 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3801. Min Act: -0.1700
Data Index: 2463834 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9113. Min Range: -5.9113
Max Act: 5.3801. Min Act: -0.1700
Data Index: 2022800 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19