Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5514 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.3476. Min Act: -0.1700
Data Index: 1650862 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.2539. Min Act: -0.1700
Data Index: 5777699 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.0976. Min Act: -0.1700
Data Index: 1779084 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.1289. Min Act: -0.1700
Data Index: 5716618 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.0664. Min Act: -0.1700
Data Index: 3679387 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.0351. Min Act: -0.1700
Data Index: 8793794 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.0664. Min Act: -0.1700
Data Index: 1584940 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.0351. Min Act: -0.1700
Data Index: 506368 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3476. Min Range: -7.3476
Max Act: 7.0351. Min Act: -0.1700
Data Index: 59265 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.9414. Min Act: -0.1700
Data Index: 1209526 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.9414. Min Act: -0.1700
Data Index: 4353831 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.9414. Min Act: -0.1700
Data Index: 2502374 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.8789. Min Act: -0.1700
Data Index: 3022961 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.8789. Min Act: -0.1700
Data Index: 832692 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.9101. Min Act: -0.1700
Data Index: 6807424 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.8476. Min Act: -0.1700
Data Index: 8464270 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.8789. Min Act: -0.1700
Data Index: 5697271 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.8476. Min Act: -0.1700
Data Index: 6297202 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.8476. Min Act: -0.1700
Data Index: 3411639 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3476. Min Range: -7.3476
Max Act: 6.7851. Min Act: -0.1700
Data Index: 3122013 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19