Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1684 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.9583. Min Act: -0.1700
Data Index: 5231286 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.6458. Min Act: -0.1700
Data Index: 6663170 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.6458. Min Act: -0.1700
Data Index: 7390497 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.3333. Min Act: -0.1700
Data Index: 3198933 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.3020. Min Act: -0.1700
Data Index: 6162581 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.2083. Min Act: -0.1700
Data Index: 3941783 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.1458. Min Act: -0.1700
Data Index: 4538075 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.1770. Min Act: -0.1700
Data Index: 6665294 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.1458. Min Act: -0.1700
Data Index: 5875092 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.1458. Min Act: -0.1700
Data Index: 7127923 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.1145. Min Act: -0.1700
Data Index: 1242227 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.1458. Min Act: -0.1700
Data Index: 916692 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.0833. Min Act: -0.1700
Data Index: 1096731 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.0520. Min Act: -0.1700
Data Index: 6307846 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.0833. Min Act: -0.1700
Data Index: 6852640 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.0833. Min Act: -0.1700
Data Index: 7406125 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.0520. Min Act: -0.1700
Data Index: 3130235 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.0208. Min Act: -0.1700
Data Index: 6315398 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.0208. Min Act: -0.1700
Data Index: 2661422 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9583. Min Range: -6.9583
Max Act: 5.9895. Min Act: -0.1700
Data Index: 4312072 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19