Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 978 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.5311. Min Act: -0.1700
Data Index: 3197759 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.3436. Min Act: -0.1700
Data Index: 5449696 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.3123. Min Act: -0.1700
Data Index: 5420505 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.2811. Min Act: -0.1700
Data Index: 4995699 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.2811. Min Act: -0.1700
Data Index: 4312135 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.2498. Min Act: -0.1700
Data Index: 2103882 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.2498. Min Act: -0.1700
Data Index: 6791152 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.2498. Min Act: -0.1700
Data Index: 5144887 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.2186. Min Act: -0.1700
Data Index: 1544373 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.2186. Min Act: -0.1700
Data Index: 1426613 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.2186. Min Act: -0.1700
Data Index: 2828115 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.1873. Min Act: -0.1700
Data Index: 8827551 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.1873. Min Act: -0.1700
Data Index: 5827846 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.0623. Min Act: -0.1700
Data Index: 190628 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.0623. Min Act: -0.1700
Data Index: 1650423 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5311. Min Range: -7.5311
Max Act: 6.9998. Min Act: -0.1700
Data Index: 8615693 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.0311. Min Act: -0.1700
Data Index: 5596842 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.0311. Min Act: -0.1700
Data Index: 5841615 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5311. Min Range: -7.5311
Max Act: 7.0311. Min Act: -0.1700
Data Index: 8011410 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5311. Min Range: -7.5311
Max Act: 6.9686. Min Act: -0.1700
Data Index: 6930336 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19