Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6352 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1367. Min Range: -7.1367
Max Act: 7.1367. Min Act: -0.1700
Data Index: 1050852 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1367. Min Range: -7.1367
Max Act: 7.1054. Min Act: -0.1700
Data Index: 1074473 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1367. Min Range: -7.1367
Max Act: 7.1054. Min Act: -0.1700
Data Index: 5848814 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1367. Min Range: -7.1367
Max Act: 7.0429. Min Act: -0.1700
Data Index: 813875 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1367. Min Range: -7.1367
Max Act: 7.0117. Min Act: -0.1700
Data Index: 955471 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1367. Min Range: -7.1367
Max Act: 7.0117. Min Act: -0.1700
Data Index: 3832784 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.9804. Min Act: -0.1700
Data Index: 5706261 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.9804. Min Act: -0.1700
Data Index: 1779864 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.9179. Min Act: -0.1700
Data Index: 8709949 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8867. Min Act: -0.1700
Data Index: 4451557 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8554. Min Act: -0.1700
Data Index: 7560794 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8554. Min Act: -0.1700
Data Index: 4828402 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8554. Min Act: -0.1700
Data Index: 8450266 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8554. Min Act: -0.1700
Data Index: 1228580 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8554. Min Act: -0.1700
Data Index: 7933797 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8554. Min Act: -0.1700
Data Index: 577600 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8242. Min Act: -0.1700
Data Index: 4846619 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.8242. Min Act: -0.1700
Data Index: 7350153 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.7929. Min Act: -0.1700
Data Index: 1993189 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1367. Min Range: -7.1367
Max Act: 6.7617. Min Act: -0.1700
Data Index: 2601890 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19