Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.4050. Min Act: -0.1700
Data Index: 1644674 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.4050. Min Act: -0.1700
Data Index: 4511070 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.3738. Min Act: -0.1700
Data Index: 5839986 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.3425. Min Act: -0.1700
Data Index: 5770557 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.3113. Min Act: -0.1700
Data Index: 3904174 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.3425. Min Act: -0.1700
Data Index: 8209014 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.2800. Min Act: -0.1700
Data Index: 3945241 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.2175. Min Act: -0.1700
Data Index: 3136640 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1863. Min Act: -0.1700
Data Index: 30110 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1550. Min Act: -0.1700
Data Index: 1039861 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1550. Min Act: -0.1700
Data Index: 5688271 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1550. Min Act: -0.1700
Data Index: 2919357 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1238. Min Act: -0.1700
Data Index: 1396598 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1238. Min Act: -0.1700
Data Index: 328802 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.0613. Min Act: -0.1700
Data Index: 3704909 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.1238. Min Act: -0.1700
Data Index: 660039 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.0925. Min Act: -0.1700
Data Index: 2023955 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.0613. Min Act: -0.1700
Data Index: 7425596 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4050. Min Range: -6.4050
Max Act: 6.0613. Min Act: -0.1700
Data Index: 3730677 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4050. Min Range: -6.4050
Max Act: 5.9988. Min Act: -0.1700
Data Index: 3905840 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19