Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5418 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.6458. Min Act: -0.1700
Data Index: 753872 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.5521. Min Act: -0.1700
Data Index: 6444073 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.5208. Min Act: -0.1700
Data Index: 3048297 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.5208. Min Act: -0.1700
Data Index: 2979766 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.4583. Min Act: -0.1700
Data Index: 7442021 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.4271. Min Act: -0.1700
Data Index: 2227399 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.3021. Min Act: -0.1700
Data Index: 1628045 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.3021. Min Act: -0.1700
Data Index: 6444074 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.2708. Min Act: -0.1700
Data Index: 473453 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.2396. Min Act: -0.1700
Data Index: 2469593 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.2708. Min Act: -0.1700
Data Index: 4642385 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.2396. Min Act: -0.1700
Data Index: 3640045 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.2396. Min Act: -0.1700
Data Index: 1538921 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.2083. Min Act: -0.1700
Data Index: 1611392 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.2083. Min Act: -0.1700
Data Index: 2411327 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.1771. Min Act: -0.1700
Data Index: 2624931 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.1458. Min Act: -0.1700
Data Index: 7736773 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.1458. Min Act: -0.1700
Data Index: 494444 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.1771. Min Act: -0.1700
Data Index: 7818243 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6458. Min Range: -6.6458
Max Act: 6.1771. Min Act: -0.1700
Data Index: 6138484 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19