Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.4607. Min Act: -0.1700
Data Index: 5185383 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.4607. Min Act: -0.1700
Data Index: 5371615 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.3357. Min Act: -0.1700
Data Index: 400697 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.2732. Min Act: -0.1700
Data Index: 6557562 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.2732. Min Act: -0.1700
Data Index: 706258 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.2420. Min Act: -0.1700
Data Index: 8142048 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.2732. Min Act: -0.1700
Data Index: 1186335 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.1482. Min Act: -0.1700
Data Index: 2511999 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.1795. Min Act: -0.1700
Data Index: 1171481 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.1482. Min Act: -0.1700
Data Index: 7058209 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.1795. Min Act: -0.1700
Data Index: 2511356 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.1170. Min Act: -0.1700
Data Index: 1694493 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.1170. Min Act: -0.1700
Data Index: 3732902 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.0545. Min Act: -0.1700
Data Index: 7773836 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.0232. Min Act: -0.1700
Data Index: 5102056 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.0232. Min Act: -0.1700
Data Index: 6605909 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4607. Min Range: -8.4607
Max Act: 8.0232. Min Act: -0.1700
Data Index: 5824099 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4607. Min Range: -8.4607
Max Act: 7.9920. Min Act: -0.1700
Data Index: 3208050 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4607. Min Range: -8.4607
Max Act: 7.9920. Min Act: -0.1700
Data Index: 1694494 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4607. Min Range: -8.4607
Max Act: 7.9920. Min Act: -0.1700
Data Index: 701389 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19