Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.6924. Min Act: -0.1700
Data Index: 1209249 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.5987. Min Act: -0.1700
Data Index: 7626003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.5987. Min Act: -0.1700
Data Index: 7873747 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.5362. Min Act: -0.1700
Data Index: 1824117 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.5049. Min Act: -0.1700
Data Index: 6731072 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.4737. Min Act: -0.1700
Data Index: 61133 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.4737. Min Act: -0.1700
Data Index: 1679504 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.4424. Min Act: -0.1700
Data Index: 216459 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.4424. Min Act: -0.1700
Data Index: 6031123 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.4112. Min Act: -0.1700
Data Index: 588288 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3799. Min Act: -0.1700
Data Index: 7631866 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3799. Min Act: -0.1700
Data Index: 8396408 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3799. Min Act: -0.1700
Data Index: 1968336 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3487. Min Act: -0.1700
Data Index: 7419815 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3487. Min Act: -0.1700
Data Index: 5532338 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3174. Min Act: -0.1700
Data Index: 2152127 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3174. Min Act: -0.1700
Data Index: 6487101 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3174. Min Act: -0.1700
Data Index: 1679505 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.2862. Min Act: -0.1700
Data Index: 1454057 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6924. Min Range: -6.6924
Max Act: 6.3174. Min Act: -0.1700
Data Index: 4814064 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19