Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2387. Min Range: -7.2387
Max Act: 7.2387. Min Act: -0.1700
Data Index: 6581221 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2387. Min Range: -7.2387
Max Act: 7.1762. Min Act: -0.1700
Data Index: 5647112 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2387. Min Range: -7.2387
Max Act: 7.1450. Min Act: -0.1700
Data Index: 3861772 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2387. Min Range: -7.2387
Max Act: 7.0200. Min Act: -0.1700
Data Index: 8382160 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.9887. Min Act: -0.1700
Data Index: 4528116 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2387. Min Range: -7.2387
Max Act: 7.0200. Min Act: -0.1700
Data Index: 4324275 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.9262. Min Act: -0.1700
Data Index: 2842410 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.8637. Min Act: -0.1700
Data Index: 1459238 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.8637. Min Act: -0.1700
Data Index: 5751146 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.8637. Min Act: -0.1700
Data Index: 8311872 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.8012. Min Act: -0.1700
Data Index: 4571501 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.7700. Min Act: -0.1700
Data Index: 8755233 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.7387. Min Act: -0.1700
Data Index: 2842407 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.7075. Min Act: -0.1700
Data Index: 471471 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.6762. Min Act: -0.1700
Data Index: 869304 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.6450. Min Act: -0.1700
Data Index: 6795396 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.6137. Min Act: -0.1700
Data Index: 6453711 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1501799 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1312879 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2387. Min Range: -7.2387
Max Act: 6.5825. Min Act: -0.1700
Data Index: 4441704 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19