Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3996 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9895. Min Range: -7.9895
Max Act: 7.9895. Min Act: -0.1700
Data Index: 3427088 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9895. Min Range: -7.9895
Max Act: 7.1145. Min Act: -0.1700
Data Index: 2015757 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9895. Min Range: -7.9895
Max Act: 7.0833. Min Act: -0.1700
Data Index: 2573256 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9895. Min Range: -7.9895
Max Act: 7.0208. Min Act: -0.1700
Data Index: 4533243 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.9583. Min Act: -0.1700
Data Index: 3478665 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.8645. Min Act: -0.1700
Data Index: 168129 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.8645. Min Act: -0.1700
Data Index: 4799235 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.8333. Min Act: -0.1700
Data Index: 4411642 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.8333. Min Act: -0.1700
Data Index: 905866 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.8020. Min Act: -0.1700
Data Index: 7916032 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.8020. Min Act: -0.1700
Data Index: 3718291 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.8020. Min Act: -0.1700
Data Index: 2671074 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.7395. Min Act: -0.1700
Data Index: 6882676 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.7395. Min Act: -0.1700
Data Index: 5144334 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.7083. Min Act: -0.1700
Data Index: 6337680 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.7083. Min Act: -0.1700
Data Index: 6415227 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.6770. Min Act: -0.1700
Data Index: 268252 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.7083. Min Act: -0.1700
Data Index: 1839387 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.6770. Min Act: -0.1700
Data Index: 4629877 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9895. Min Range: -7.9895
Max Act: 6.6458. Min Act: -0.1700
Data Index: 2982557 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19