Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.7077. Min Act: -0.1700
Data Index: 2829441 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.4577. Min Act: -0.1700
Data Index: 4357259 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.4264. Min Act: -0.1700
Data Index: 8788339 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.3639. Min Act: -0.1700
Data Index: 3882713 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.3639. Min Act: -0.1700
Data Index: 4199119 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.1764. Min Act: -0.1700
Data Index: 1475034 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.1764. Min Act: -0.1700
Data Index: 8604292 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.1452. Min Act: -0.1700
Data Index: 6541636 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.1452. Min Act: -0.1700
Data Index: 568215 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.1139. Min Act: -0.1700
Data Index: 3657033 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0827. Min Act: -0.1700
Data Index: 695332 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0827. Min Act: -0.1700
Data Index: 8718478 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0827. Min Act: -0.1700
Data Index: 3805690 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0827. Min Act: -0.1700
Data Index: 1862051 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0514. Min Act: -0.1700
Data Index: 7774698 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0514. Min Act: -0.1700
Data Index: 1844706 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0514. Min Act: -0.1700
Data Index: 1475029 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0514. Min Act: -0.1700
Data Index: 2782115 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0514. Min Act: -0.1700
Data Index: 2564921 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7077. Min Range: -7.7077
Max Act: 7.0202. Min Act: -0.1700
Data Index: 6199160 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19