Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0658. Min Range: -3.0658
Max Act: 3.0658. Min Act: -0.1700
Data Index: 7289532 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9868. Min Act: -0.1700
Data Index: 2096936 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.9235. Min Act: -0.1700
Data Index: 3157896 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8918. Min Act: -0.1700
Data Index: 1185186 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8759. Min Act: -0.1700
Data Index: 4999860 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8283. Min Act: -0.1700
Data Index: 2667534 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8442. Min Act: -0.1700
Data Index: 8084229 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.8124. Min Act: -0.1700
Data Index: 3622629 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7964. Min Act: -0.1700
Data Index: 2942887 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7805. Min Act: -0.1700
Data Index: 1606218 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7486. Min Act: -0.1700
Data Index: 7976568 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7805. Min Act: -0.1700
Data Index: 1407143 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7646. Min Act: -0.1700
Data Index: 1537133 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7646. Min Act: -0.1700
Data Index: 388174 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7646. Min Act: -0.1700
Data Index: 1363263 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7486. Min Act: -0.1700
Data Index: 2255916 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7486. Min Act: -0.1700
Data Index: 3493579 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7486. Min Act: -0.1700
Data Index: 4363092 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7486. Min Act: -0.1700
Data Index: 5396931 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0658. Min Range: -3.0658
Max Act: 2.7326. Min Act: -0.1700
Data Index: 7676971 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19