Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2335 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.4367. Min Act: -0.1700
Data Index: 1826439 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.2492. Min Act: -0.1700
Data Index: 5710778 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.2180. Min Act: -0.1700
Data Index: 4246829 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.1555. Min Act: -0.1700
Data Index: 805301 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.1555. Min Act: -0.1700
Data Index: 7115557 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.1242. Min Act: -0.1700
Data Index: 2078440 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.1242. Min Act: -0.1700
Data Index: 1166782 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.1242. Min Act: -0.1700
Data Index: 7093329 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.1242. Min Act: -0.1700
Data Index: 5948667 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.0930. Min Act: -0.1700
Data Index: 1468477 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.0617. Min Act: -0.1700
Data Index: 1608169 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.0617. Min Act: -0.1700
Data Index: 8823617 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.0617. Min Act: -0.1700
Data Index: 5371645 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4367. Min Range: -6.4367
Max Act: 5.9992. Min Act: -0.1700
Data Index: 8538493 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4367. Min Range: -6.4367
Max Act: 6.0305. Min Act: -0.1700
Data Index: 6546629 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4367. Min Range: -6.4367
Max Act: 5.9992. Min Act: -0.1700
Data Index: 3201294 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4367. Min Range: -6.4367
Max Act: 5.9992. Min Act: -0.1700
Data Index: 3693970 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4367. Min Range: -6.4367
Max Act: 5.9992. Min Act: -0.1700
Data Index: 4882186 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4367. Min Range: -6.4367
Max Act: 5.9992. Min Act: -0.1700
Data Index: 755678 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4367. Min Range: -6.4367
Max Act: 5.9992. Min Act: -0.1700
Data Index: 4465214 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19