Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 921 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.9052. Min Act: -0.1700
Data Index: 3696026 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.9052. Min Act: -0.1700
Data Index: 3095700 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.7802. Min Act: -0.1700
Data Index: 2460501 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.7489. Min Act: -0.1700
Data Index: 3611509 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.7177. Min Act: -0.1700
Data Index: 7036352 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.7489. Min Act: -0.1700
Data Index: 338459 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.7177. Min Act: -0.1700
Data Index: 4184821 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.7177. Min Act: -0.1700
Data Index: 874936 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.7177. Min Act: -0.1700
Data Index: 1782841 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.7177. Min Act: -0.1700
Data Index: 2460500 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6552. Min Act: -0.1700
Data Index: 308452 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6864. Min Act: -0.1700
Data Index: 7351065 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6864. Min Act: -0.1700
Data Index: 5879106 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6864. Min Act: -0.1700
Data Index: 1896293 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6552. Min Act: -0.1700
Data Index: 7507899 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6864. Min Act: -0.1700
Data Index: 1840084 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6864. Min Act: -0.1700
Data Index: 5730621 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6552. Min Act: -0.1699
Data Index: 3159151 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6552. Min Act: -0.1700
Data Index: 2430491 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9052. Min Range: -4.9052
Max Act: 4.6552. Min Act: -0.1700
Data Index: 7318862 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19