Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2872. Min Range: -7.2872
Max Act: 7.2872. Min Act: -0.1700
Data Index: 7764445 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2872. Min Range: -7.2872
Max Act: 7.2247. Min Act: -0.1700
Data Index: 8165137 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2872. Min Range: -7.2872
Max Act: 7.0372. Min Act: -0.1700
Data Index: 246900 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2872. Min Range: -7.2872
Max Act: 7.0685. Min Act: -0.1700
Data Index: 4266852 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.9435. Min Act: -0.1700
Data Index: 6114128 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.8497. Min Act: -0.1700
Data Index: 4533347 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.8497. Min Act: -0.1700
Data Index: 5713726 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.8185. Min Act: -0.1700
Data Index: 6346354 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.7872. Min Act: -0.1700
Data Index: 2092474 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.7247. Min Act: -0.1700
Data Index: 4797012 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6935. Min Act: -0.1700
Data Index: 4232127 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6935. Min Act: -0.1700
Data Index: 3581374 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6935. Min Act: -0.1700
Data Index: 2829899 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6935. Min Act: -0.1700
Data Index: 6838128 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6935. Min Act: -0.1700
Data Index: 6811605 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6935. Min Act: -0.1700
Data Index: 1862593 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6622. Min Act: -0.1700
Data Index: 3336857 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6622. Min Act: -0.1700
Data Index: 518173 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6622. Min Act: -0.1700
Data Index: 4545814 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2872. Min Range: -7.2872
Max Act: 6.6622. Min Act: -0.1700
Data Index: 4405451 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19