Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2663 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.3189. Min Act: -0.1700
Data Index: 283539 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.3013. Min Act: -0.1700
Data Index: 160234 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2660. Min Act: -0.1700
Data Index: 8160342 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2483. Min Act: -0.1700
Data Index: 849335 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2307. Min Act: -0.1700
Data Index: 4230843 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2483. Min Act: -0.1700
Data Index: 1856008 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2131. Min Act: -0.1700
Data Index: 897922 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2307. Min Act: -0.1700
Data Index: 6861543 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2131. Min Act: -0.1700
Data Index: 8198253 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2131. Min Act: -0.1700
Data Index: 8333622 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2131. Min Act: -0.1700
Data Index: 6061493 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2131. Min Act: -0.1700
Data Index: 3750794 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2131. Min Act: -0.1700
Data Index: 6364919 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2307. Min Act: -0.1700
Data Index: 2115350 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.2131. Min Act: -0.1700
Data Index: 2096323 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.1955. Min Act: -0.1700
Data Index: 1812480 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.1955. Min Act: -0.1700
Data Index: 474302 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.1779. Min Act: -0.1700
Data Index: 3004179 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.1955. Min Act: -0.1700
Data Index: 352090 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3189. Min Range: -1.3189
Max Act: 1.1955. Min Act: -0.1700
Data Index: 3452502 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19