Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6246 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2049. Min Range: -9.2049
Max Act: 9.2049. Min Act: -0.1700
Data Index: 2976613 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2049. Min Range: -9.2049
Max Act: 9.0799. Min Act: -0.1700
Data Index: 5083034 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.9549. Min Act: -0.1700
Data Index: 6281402 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.9549. Min Act: -0.1700
Data Index: 3866687 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.9549. Min Act: -0.1700
Data Index: 5682439 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.8924. Min Act: -0.1700
Data Index: 7917290 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.8299. Min Act: -0.1700
Data Index: 6065336 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.8924. Min Act: -0.1700
Data Index: 785618 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.8924. Min Act: -0.1700
Data Index: 862767 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.8299. Min Act: -0.1700
Data Index: 5841567 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.7674. Min Act: -0.1700
Data Index: 2451717 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.7049. Min Act: -0.1700
Data Index: 1170337 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.7049. Min Act: -0.1700
Data Index: 7435734 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.7049. Min Act: -0.1700
Data Index: 2651032 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.7049. Min Act: -0.1700
Data Index: 1789791 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.7049. Min Act: -0.1700
Data Index: 1956887 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.7049. Min Act: -0.1700
Data Index: 8018101 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.6424. Min Act: -0.1700
Data Index: 7009907 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.6424. Min Act: -0.1700
Data Index: 5802126 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2049. Min Range: -9.2049
Max Act: 8.6424. Min Act: -0.1700
Data Index: 4540842 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19