Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2029 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.6954. Min Act: -0.1700
Data Index: 662775 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.4454. Min Act: -0.1700
Data Index: 1826931 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.3829. Min Act: -0.1700
Data Index: 7701042 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.3204. Min Act: -0.1700
Data Index: 7289683 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.2579. Min Act: -0.1700
Data Index: 1034570 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.2266. Min Act: -0.1700
Data Index: 3601644 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.2579. Min Act: -0.1700
Data Index: 1894392 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.1641. Min Act: -0.1700
Data Index: 3993688 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.1641. Min Act: -0.1700
Data Index: 1058325 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.1954. Min Act: -0.1700
Data Index: 6238097 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.1329. Min Act: -0.1700
Data Index: 1413195 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.1016. Min Act: -0.1700
Data Index: 3066383 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.0704. Min Act: -0.1700
Data Index: 5049073 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.0391. Min Act: -0.1700
Data Index: 4783711 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.0391. Min Act: -0.1700
Data Index: 3507068 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.0391. Min Act: -0.1700
Data Index: 1242067 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.0391. Min Act: -0.1700
Data Index: 8107715 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6954. Min Range: -7.6954
Max Act: 6.9766. Min Act: -0.1700
Data Index: 8206385 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6954. Min Range: -7.6954
Max Act: 6.9766. Min Act: -0.1700
Data Index: 8135842 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6954. Min Range: -7.6954
Max Act: 7.0079. Min Act: -0.1700
Data Index: 6109465 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19