Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4439 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.9931. Min Act: -0.1700
Data Index: 1804081 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.9306. Min Act: -0.1700
Data Index: 3800316 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.8369. Min Act: -0.1700
Data Index: 8360335 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.8369. Min Act: -0.1700
Data Index: 2106152 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.8056. Min Act: -0.1700
Data Index: 1171822 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.8056. Min Act: -0.1700
Data Index: 4933453 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.7119. Min Act: -0.1700
Data Index: 6478258 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.7119. Min Act: -0.1700
Data Index: 6037932 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6806. Min Act: -0.1700
Data Index: 7744208 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6806. Min Act: -0.1700
Data Index: 2911650 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6494. Min Act: -0.1700
Data Index: 1896277 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6494. Min Act: -0.1700
Data Index: 2373245 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6494. Min Act: -0.1700
Data Index: 19375 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6494. Min Act: -0.1700
Data Index: 7554946 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6494. Min Act: -0.1700
Data Index: 6982053 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6181. Min Act: -0.1700
Data Index: 510824 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6181. Min Act: -0.1700
Data Index: 2965370 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6181. Min Act: -0.1700
Data Index: 6681657 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6181. Min Act: -0.1700
Data Index: 6254669 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5869. Min Act: -0.1700
Data Index: 6142047 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19