Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.3639. Min Act: -0.1700
Data Index: 3457067 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.3014. Min Act: -0.1700
Data Index: 6967276 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.2389. Min Act: -0.1700
Data Index: 1162230 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.2077. Min Act: -0.1700
Data Index: 1536997 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.1764. Min Act: -0.1700
Data Index: 7380311 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.1764. Min Act: -0.1700
Data Index: 4221719 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.1452. Min Act: -0.1700
Data Index: 8693934 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.1764. Min Act: -0.1700
Data Index: 3430598 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.1452. Min Act: -0.1700
Data Index: 1529001 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.1452. Min Act: -0.1700
Data Index: 7846735 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.1139. Min Act: -0.1700
Data Index: 5734559 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.1452. Min Act: -0.1700
Data Index: 6265119 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.0827. Min Act: -0.1700
Data Index: 1878607 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.0827. Min Act: -0.1700
Data Index: 2214042 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.0827. Min Act: -0.1700
Data Index: 8136843 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.0827. Min Act: -0.1700
Data Index: 1749506 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.0514. Min Act: -0.1700
Data Index: 5272014 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.0827. Min Act: -0.1700
Data Index: 283379 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.0202. Min Act: -0.1700
Data Index: 6971035 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3639. Min Range: -5.3639
Max Act: 5.0514. Min Act: -0.1700
Data Index: 3500781 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19