Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2322 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0741. Min Range: -9.0741
Max Act: 9.0741. Min Act: -0.1700
Data Index: 4186398 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.8241. Min Act: -0.1700
Data Index: 1063735 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.7616. Min Act: -0.1700
Data Index: 4096175 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.7616. Min Act: -0.1700
Data Index: 5673282 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.6366. Min Act: -0.1700
Data Index: 958471 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.5741. Min Act: -0.1700
Data Index: 4351687 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.5116. Min Act: -0.1700
Data Index: 6133485 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.4491. Min Act: -0.1700
Data Index: 5371547 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.4491. Min Act: -0.1700
Data Index: 2176049 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.4491. Min Act: -0.1700
Data Index: 3159074 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3866. Min Act: -0.1700
Data Index: 7956178 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3866. Min Act: -0.1700
Data Index: 4093804 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3866. Min Act: -0.1700
Data Index: 2655886 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3866. Min Act: -0.1700
Data Index: 365455 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3866. Min Act: -0.1700
Data Index: 2169844 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3866. Min Act: -0.1700
Data Index: 639631 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3241. Min Act: -0.1700
Data Index: 924629 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.2616. Min Act: -0.1700
Data Index: 4933512 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3866. Min Act: -0.1700
Data Index: 5588857 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0741. Min Range: -9.0741
Max Act: 8.3241. Min Act: -0.1700
Data Index: 4564868 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19