Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4596 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.4950. Min Act: -0.1700
Data Index: 1235850 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.4950. Min Act: -0.1700
Data Index: 1153839 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.3075. Min Act: -0.1700
Data Index: 6157788 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.2137. Min Act: -0.1700
Data Index: 3880347 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.1512. Min Act: -0.1700
Data Index: 7421426 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.1200. Min Act: -0.1700
Data Index: 4628728 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.1200. Min Act: -0.1700
Data Index: 1909130 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0887. Min Act: -0.1700
Data Index: 5410260 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0887. Min Act: -0.1700
Data Index: 1484785 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0575. Min Act: -0.1700
Data Index: 7291962 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0575. Min Act: -0.1700
Data Index: 1839853 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0575. Min Act: -0.1700
Data Index: 6790693 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0575. Min Act: -0.1700
Data Index: 8055759 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0262. Min Act: -0.1700
Data Index: 1071956 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0887. Min Act: -0.1700
Data Index: 3463106 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0262. Min Act: -0.1700
Data Index: 4500106 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4950. Min Range: -7.4950
Max Act: 6.9950. Min Act: -0.1700
Data Index: 1992618 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4950. Min Range: -7.4950
Max Act: 6.9637. Min Act: -0.1700
Data Index: 2675032 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4950. Min Range: -7.4950
Max Act: 7.0262. Min Act: -0.1700
Data Index: 7158310 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4950. Min Range: -7.4950
Max Act: 6.9637. Min Act: -0.1700
Data Index: 6390058 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19