Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3809 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.4040. Min Act: -0.1700
Data Index: 6265856 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.3415. Min Act: -0.1700
Data Index: 2471374 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.3103. Min Act: -0.1700
Data Index: 6971513 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.3415. Min Act: -0.1700
Data Index: 5043362 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.2790. Min Act: -0.1700
Data Index: 6596806 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.2165. Min Act: -0.1700
Data Index: 2328333 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.2478. Min Act: -0.1700
Data Index: 8681399 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.2165. Min Act: -0.1700
Data Index: 2942064 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.2165. Min Act: -0.1700
Data Index: 299148 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.1853. Min Act: -0.1700
Data Index: 7673775 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.2165. Min Act: -0.1700
Data Index: 7162767 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.1853. Min Act: -0.1700
Data Index: 8208059 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.1540. Min Act: -0.1700
Data Index: 1537597 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.1228. Min Act: -0.1700
Data Index: 8345283 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.1228. Min Act: -0.1700
Data Index: 1494343 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.1228. Min Act: -0.1700
Data Index: 8164461 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.1228. Min Act: -0.1700
Data Index: 1715904 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.0915. Min Act: -0.1700
Data Index: 5633503 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.0915. Min Act: -0.1700
Data Index: 4944533 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4040. Min Range: -5.4040
Max Act: 5.1228. Min Act: -0.1700
Data Index: 6593695 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19