Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2751 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.5349. Min Act: -0.1700
Data Index: 3993501 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.4412. Min Act: -0.1700
Data Index: 7562251 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.4724. Min Act: -0.1700
Data Index: 5422768 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.3474. Min Act: -0.1700
Data Index: 7038047 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.3787. Min Act: -0.1700
Data Index: 7563183 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.3787. Min Act: -0.1700
Data Index: 149586 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.3162. Min Act: -0.1700
Data Index: 2033 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.3787. Min Act: -0.1700
Data Index: 3734691 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.2224. Min Act: -0.1700
Data Index: 502859 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.1599. Min Act: -0.1700
Data Index: 258964 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.1599. Min Act: -0.1700
Data Index: 2313691 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.1599. Min Act: -0.1700
Data Index: 1296694 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.1287. Min Act: -0.1700
Data Index: 3526729 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.1287. Min Act: -0.1700
Data Index: 1501540 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.1599. Min Act: -0.1700
Data Index: 914710 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.0662. Min Act: -0.1700
Data Index: 3126326 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.0974. Min Act: -0.1700
Data Index: 5472539 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.0662. Min Act: -0.1700
Data Index: 3437929 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.0662. Min Act: -0.1700
Data Index: 4467404 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5349. Min Range: -6.5349
Max Act: 6.0974. Min Act: -0.1700
Data Index: 2905229 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19