Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 615 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.8950. Min Act: -0.1700
Data Index: 7795374 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.6762. Min Act: -0.1700
Data Index: 1204992 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.5825. Min Act: -0.1700
Data Index: 5856902 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.5512. Min Act: -0.1700
Data Index: 8196641 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.5200. Min Act: -0.1700
Data Index: 2189742 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.4575. Min Act: -0.1700
Data Index: 8260774 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.4575. Min Act: -0.1700
Data Index: 314812 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.4575. Min Act: -0.1700
Data Index: 4091400 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.4262. Min Act: -0.1700
Data Index: 2189744 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.4262. Min Act: -0.1700
Data Index: 730715 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.3950. Min Act: -0.1700
Data Index: 4914390 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.4262. Min Act: -0.1700
Data Index: 3414215 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.3637. Min Act: -0.1700
Data Index: 3017483 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.3325. Min Act: -0.1700
Data Index: 6101163 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.3325. Min Act: -0.1700
Data Index: 72445 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.3012. Min Act: -0.1700
Data Index: 7974569 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.3012. Min Act: -0.1700
Data Index: 3044794 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.3325. Min Act: -0.1700
Data Index: 6852983 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.2700. Min Act: -0.1700
Data Index: 3415788 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8950. Min Range: -5.8950
Max Act: 5.2075. Min Act: -0.1700
Data Index: 6547565 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19