Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0331. Min Range: -8.0331
Max Act: 8.0331. Min Act: -0.1700
Data Index: 8076155 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.8769. Min Act: -0.1700
Data Index: 3028821 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.8456. Min Act: -0.1700
Data Index: 1020421 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.8144. Min Act: -0.1700
Data Index: 5747859 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.7519. Min Act: -0.1700
Data Index: 1623141 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.6269. Min Act: -0.1700
Data Index: 5615321 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.6581. Min Act: -0.1700
Data Index: 3588114 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.6269. Min Act: -0.1700
Data Index: 1827227 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.5956. Min Act: -0.1700
Data Index: 1875213 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.5644. Min Act: -0.1700
Data Index: 4565028 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.5019. Min Act: -0.1700
Data Index: 800276 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.4706. Min Act: -0.1700
Data Index: 4417995 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.3769. Min Act: -0.1700
Data Index: 362308 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.3769. Min Act: -0.1700
Data Index: 7913581 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.3769. Min Act: -0.1700
Data Index: 3146784 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.3456. Min Act: -0.1700
Data Index: 3927953 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.3456. Min Act: -0.1700
Data Index: 5687817 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.3456. Min Act: -0.1700
Data Index: 6039035 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.3456. Min Act: -0.1700
Data Index: 1219640 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0331. Min Range: -8.0331
Max Act: 7.3456. Min Act: -0.1700
Data Index: 2294772 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19