Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.6910. Min Act: -0.1700
Data Index: 2315253 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.5660. Min Act: -0.1700
Data Index: 3409208 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.5660. Min Act: -0.1700
Data Index: 1658901 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.5347. Min Act: -0.1700
Data Index: 620960 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.5347. Min Act: -0.1700
Data Index: 4150579 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.5035. Min Act: -0.1700
Data Index: 444060 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.5035. Min Act: -0.1700
Data Index: 4739316 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.4722. Min Act: -0.1700
Data Index: 5723337 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.4097. Min Act: -0.1700
Data Index: 7995201 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.4097. Min Act: -0.1700
Data Index: 4945552 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.3785. Min Act: -0.1700
Data Index: 1585659 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.3472. Min Act: -0.1700
Data Index: 391122 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.3160. Min Act: -0.1700
Data Index: 6145868 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.3160. Min Act: -0.1700
Data Index: 8443618 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.3472. Min Act: -0.1700
Data Index: 6176809 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.3160. Min Act: -0.1700
Data Index: 8171357 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.3160. Min Act: -0.1700
Data Index: 1339319 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.3160. Min Act: -0.1700
Data Index: 4510171 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.2847. Min Act: -0.1700
Data Index: 3787190 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6910. Min Range: -4.6910
Max Act: 4.2847. Min Act: -0.1700
Data Index: 3938536 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19