Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5538 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.8712. Min Act: -0.1700
Data Index: 2610509 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.8399. Min Act: -0.1700
Data Index: 3301565 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.8399. Min Act: -0.1700
Data Index: 8385498 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.8087. Min Act: -0.1700
Data Index: 8553719 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7462. Min Act: -0.1700
Data Index: 473214 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7774. Min Act: -0.1700
Data Index: 2763855 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7462. Min Act: -0.1700
Data Index: 7805751 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7774. Min Act: -0.1700
Data Index: 2638196 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7462. Min Act: -0.1700
Data Index: 3438169 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7462. Min Act: -0.1700
Data Index: 3943833 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7462. Min Act: -0.1700
Data Index: 8177963 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7462. Min Act: -0.1700
Data Index: 2938363 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7462. Min Act: -0.1700
Data Index: 5035960 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7462. Min Act: -0.1700
Data Index: 3752116 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7149. Min Act: -0.1700
Data Index: 4063329 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7149. Min Act: -0.1700
Data Index: 8100063 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.6837. Min Act: -0.1700
Data Index: 1580434 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7149. Min Act: -0.1700
Data Index: 4876471 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7149. Min Act: -0.1700
Data Index: 7430456 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8712. Min Range: -4.8712
Max Act: 4.7149. Min Act: -0.1700
Data Index: 6822103 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19