Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0485. Min Range: -8.0485
Max Act: 8.0485. Min Act: -0.1700
Data Index: 8321947 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.9860. Min Act: -0.1700
Data Index: 1050202 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.7985. Min Act: -0.1700
Data Index: 3075837 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.7985. Min Act: -0.1700
Data Index: 1742694 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.7360. Min Act: -0.1700
Data Index: 1093047 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.7360. Min Act: -0.1700
Data Index: 6303288 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.6735. Min Act: -0.1700
Data Index: 1750540 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.6735. Min Act: -0.1700
Data Index: 2285917 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.6110. Min Act: -0.1700
Data Index: 3269378 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.6110. Min Act: -0.1700
Data Index: 8270020 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.5485. Min Act: -0.1700
Data Index: 223705 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.5172. Min Act: -0.1700
Data Index: 4362173 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.5172. Min Act: -0.1700
Data Index: 7639440 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.4860. Min Act: -0.1700
Data Index: 1909599 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.4547. Min Act: -0.1700
Data Index: 5374262 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.4235. Min Act: -0.1700
Data Index: 4770385 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.4860. Min Act: -0.1700
Data Index: 3535321 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.4547. Min Act: -0.1700
Data Index: 2306970 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.3610. Min Act: -0.1700
Data Index: 5064708 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0485. Min Range: -8.0485
Max Act: 7.3922. Min Act: -0.1700
Data Index: 708928 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19