Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.7263. Min Act: -0.1700
Data Index: 2501963 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6950. Min Act: -0.1700
Data Index: 8391636 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.6325. Min Act: -0.1700
Data Index: 5611972 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5700. Min Act: -0.1700
Data Index: 4316463 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5075. Min Act: -0.1700
Data Index: 1310416 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5075. Min Act: -0.1700
Data Index: 6931597 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.5075. Min Act: -0.1700
Data Index: 3757142 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4763. Min Act: -0.1700
Data Index: 2425087 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4763. Min Act: -0.1700
Data Index: 1623771 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4763. Min Act: -0.1700
Data Index: 3068570 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4763. Min Act: -0.1700
Data Index: 6668970 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4450. Min Act: -0.1700
Data Index: 2648665 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4450. Min Act: -0.1700
Data Index: 4334696 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4450. Min Act: -0.1700
Data Index: 3844923 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4450. Min Act: -0.1700
Data Index: 5548524 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.3825. Min Act: -0.1700
Data Index: 949082 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4138. Min Act: -0.1700
Data Index: 1149075 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4138. Min Act: -0.1700
Data Index: 1614561 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4138. Min Act: -0.1700
Data Index: 7573609 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7263. Min Range: -5.7263
Max Act: 5.4138. Min Act: -0.1700
Data Index: 7185515 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19