Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.6211. Min Act: -0.1700
Data Index: 2847442 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.5899. Min Act: -0.1700
Data Index: 3068520 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.4336. Min Act: -0.1700
Data Index: 8087596 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.4024. Min Act: -0.1700
Data Index: 4094167 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.3711. Min Act: -0.1700
Data Index: 1470081 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.3399. Min Act: -0.1700
Data Index: 5309376 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.3399. Min Act: -0.1700
Data Index: 1448127 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.3086. Min Act: -0.1700
Data Index: 1214127 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.3086. Min Act: -0.1700
Data Index: 6956208 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.2774. Min Act: -0.1700
Data Index: 1872014 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.3086. Min Act: -0.1700
Data Index: 7974051 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.2149. Min Act: -0.1700
Data Index: 3288918 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.2149. Min Act: -0.1700
Data Index: 1591851 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.2149. Min Act: -0.1700
Data Index: 6676832 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.1524. Min Act: -0.1700
Data Index: 7326016 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.1836. Min Act: -0.1700
Data Index: 4838482 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.1524. Min Act: -0.1700
Data Index: 7598595 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.1524. Min Act: -0.1700
Data Index: 8091493 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.1524. Min Act: -0.1700
Data Index: 3138575 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6211. Min Range: -6.6211
Max Act: 6.1211. Min Act: -0.1700
Data Index: 6630924 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19