Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.6322. Min Act: -0.1700
Data Index: 259051 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.3822. Min Act: -0.1700
Data Index: 1105976 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.3197. Min Act: -0.1700
Data Index: 7271067 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.3197. Min Act: -0.1700
Data Index: 5520092 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.3822. Min Act: -0.1700
Data Index: 6088478 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.3197. Min Act: -0.1700
Data Index: 8610436 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.2572. Min Act: -0.1700
Data Index: 6864190 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.1947. Min Act: -0.1700
Data Index: 8496585 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.1947. Min Act: -0.1700
Data Index: 2734464 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.1947. Min Act: -0.1700
Data Index: 7454237 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.1947. Min Act: -0.1700
Data Index: 3497401 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.1322. Min Act: -0.1700
Data Index: 8055461 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.1322. Min Act: -0.1700
Data Index: 8332018 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.1322. Min Act: -0.1700
Data Index: 8646763 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.0697. Min Act: -0.1700
Data Index: 199592 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.0697. Min Act: -0.1700
Data Index: 7594277 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.0697. Min Act: -0.1700
Data Index: 5238791 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.0072. Min Act: -0.1700
Data Index: 8284007 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.0072. Min Act: -0.1700
Data Index: 6712965 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6322. Min Range: -9.6322
Max Act: 9.0072. Min Act: -0.1700
Data Index: 3884508 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19