Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3659 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.5304. Min Act: -0.1700
Data Index: 4643284 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.4679. Min Act: -0.1700
Data Index: 2860155 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.4367. Min Act: -0.1700
Data Index: 2132806 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.4054. Min Act: -0.1700
Data Index: 137976 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.3429. Min Act: -0.1700
Data Index: 407089 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.2804. Min Act: -0.1700
Data Index: 1913747 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.2492. Min Act: -0.1700
Data Index: 5360026 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1867. Min Act: -0.1700
Data Index: 6660025 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1867. Min Act: -0.1700
Data Index: 8679391 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1867. Min Act: -0.1700
Data Index: 2362473 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1554. Min Act: -0.1700
Data Index: 244536 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1554. Min Act: -0.1700
Data Index: 560230 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1867. Min Act: -0.1700
Data Index: 1685922 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1554. Min Act: -0.1700
Data Index: 6473564 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1242. Min Act: -0.1700
Data Index: 5067933 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1242. Min Act: -0.1700
Data Index: 719208 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1242. Min Act: -0.1700
Data Index: 6629015 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1242. Min Act: -0.1700
Data Index: 2553738 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.1242. Min Act: -0.1700
Data Index: 155363 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5304. Min Range: -5.5304
Max Act: 5.0929. Min Act: -0.1700
Data Index: 6629016 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19