Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6204 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.4292. Min Act: -0.1700
Data Index: 1939293 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.4292. Min Act: -0.1700
Data Index: 7812080 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.3979. Min Act: -0.1700
Data Index: 7283528 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.3354. Min Act: -0.1700
Data Index: 7397679 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.2417. Min Act: -0.1700
Data Index: 357372 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.1792. Min Act: -0.1700
Data Index: 2333546 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.1479. Min Act: -0.1700
Data Index: 2471866 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.1167. Min Act: -0.1700
Data Index: 1473365 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0542. Min Act: -0.1700
Data Index: 8534462 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.1167. Min Act: -0.1700
Data Index: 499923 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0854. Min Act: -0.1700
Data Index: 5505924 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0542. Min Act: -0.1700
Data Index: 2066973 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0542. Min Act: -0.1700
Data Index: 1127880 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0229. Min Act: -0.1700
Data Index: 4218661 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0542. Min Act: -0.1700
Data Index: 5256077 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0542. Min Act: -0.1700
Data Index: 4799543 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0542. Min Act: -0.1700
Data Index: 4630042 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0229. Min Act: -0.1700
Data Index: 4622285 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4292. Min Range: -5.4292
Max Act: 5.0229. Min Act: -0.1700
Data Index: 7205156 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4292. Min Range: -5.4292
Max Act: 4.9917. Min Act: -0.1700
Data Index: 28711 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19