Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.6651. Min Act: -0.1700
Data Index: 4884951 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.3526. Min Act: -0.1700
Data Index: 8577704 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.3526. Min Act: -0.1700
Data Index: 1006929 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.3526. Min Act: -0.1700
Data Index: 8233171 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.2276. Min Act: -0.1700
Data Index: 8577700 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.1651. Min Act: -0.1700
Data Index: 7621830 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.1651. Min Act: -0.1700
Data Index: 7351135 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.1651. Min Act: -0.1700
Data Index: 166025 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.0401. Min Act: -0.1700
Data Index: 7596926 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.0401. Min Act: -0.1700
Data Index: 6828599 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.0401. Min Act: -0.1700
Data Index: 8694307 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.0401. Min Act: -0.1700
Data Index: 8577702 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.0401. Min Act: -0.1700
Data Index: 7456227 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6651. Min Range: -9.6651
Max Act: 8.9776. Min Act: -0.1700
Data Index: 7593866 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6651. Min Range: -9.6651
Max Act: 9.0401. Min Act: -0.1700
Data Index: 8481824 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6651. Min Range: -9.6651
Max Act: 8.9776. Min Act: -0.1700
Data Index: 415264 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6651. Min Range: -9.6651
Max Act: 8.9151. Min Act: -0.1700
Data Index: 2199496 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6651. Min Range: -9.6651
Max Act: 8.9151. Min Act: -0.1700
Data Index: 5049663 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6651. Min Range: -9.6651
Max Act: 8.9151. Min Act: -0.1700
Data Index: 5776073 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6651. Min Range: -9.6651
Max Act: 8.9151. Min Act: -0.1700
Data Index: 8577701 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19