Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1790 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3409. Min Range: -9.3409
Max Act: 9.3409. Min Act: -0.1700
Data Index: 1732281 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3409. Min Range: -9.3409
Max Act: 9.3409. Min Act: -0.1700
Data Index: 983257 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3409. Min Range: -9.3409
Max Act: 9.2159. Min Act: -0.1700
Data Index: 582702 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.9659. Min Act: -0.1700
Data Index: 3816022 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.9659. Min Act: -0.1700
Data Index: 4356718 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.9034. Min Act: -0.1700
Data Index: 8008411 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.9034. Min Act: -0.1700
Data Index: 4773986 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.8409. Min Act: -0.1700
Data Index: 1763484 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.7784. Min Act: -0.1700
Data Index: 1875997 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.7159. Min Act: -0.1700
Data Index: 32746 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.7159. Min Act: -0.1700
Data Index: 6535561 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.6534. Min Act: -0.1700
Data Index: 1255299 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.6534. Min Act: -0.1700
Data Index: 5749847 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.6534. Min Act: -0.1700
Data Index: 2284119 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.6534. Min Act: -0.1700
Data Index: 2592829 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.5909. Min Act: -0.1700
Data Index: 712261 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.5284. Min Act: -0.1700
Data Index: 7609723 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.5909. Min Act: -0.1700
Data Index: 6266063 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.5284. Min Act: -0.1700
Data Index: 2424554 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3409. Min Range: -9.3409
Max Act: 8.5284. Min Act: -0.1700
Data Index: 7483808 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19