Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5875 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.3367. Min Act: -0.1700
Data Index: 5005236 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.3054. Min Act: -0.1700
Data Index: 2691897 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.1804. Min Act: -0.1700
Data Index: 5689746 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.1804. Min Act: -0.1700
Data Index: 8088337 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.1492. Min Act: -0.1700
Data Index: 5502414 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.1179. Min Act: -0.1700
Data Index: 70581 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.1179. Min Act: -0.1700
Data Index: 8088333 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.1179. Min Act: -0.1700
Data Index: 8098306 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.0867. Min Act: -0.1700
Data Index: 6889137 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.0554. Min Act: -0.1700
Data Index: 2574493 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.0242. Min Act: -0.1700
Data Index: 6816065 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.0242. Min Act: -0.1700
Data Index: 2574494 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3367. Min Range: -6.3367
Max Act: 6.0242. Min Act: -0.1700
Data Index: 4642712 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3367. Min Range: -6.3367
Max Act: 5.9929. Min Act: -0.1700
Data Index: 7660357 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3367. Min Range: -6.3367
Max Act: 5.9929. Min Act: -0.1700
Data Index: 3040423 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3367. Min Range: -6.3367
Max Act: 5.9929. Min Act: -0.1700
Data Index: 2096072 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3367. Min Range: -6.3367
Max Act: 5.9617. Min Act: -0.1700
Data Index: 6889133 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3367. Min Range: -6.3367
Max Act: 5.9617. Min Act: -0.1700
Data Index: 6685973 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3367. Min Range: -6.3367
Max Act: 5.9617. Min Act: -0.1700
Data Index: 4511980 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3367. Min Range: -6.3367
Max Act: 5.9617. Min Act: -0.1700
Data Index: 1141727 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19