Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5264 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0106. Min Range: -7.0106
Max Act: 7.0106. Min Act: -0.1700
Data Index: 3638707 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.7919. Min Act: -0.1700
Data Index: 6269870 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.6669. Min Act: -0.1700
Data Index: 6123403 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.6044. Min Act: -0.1700
Data Index: 4247020 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.4169. Min Act: -0.1700
Data Index: 1528074 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.3856. Min Act: -0.1700
Data Index: 2863016 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.3856. Min Act: -0.1700
Data Index: 6011151 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.3544. Min Act: -0.1700
Data Index: 5820344 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.3231. Min Act: -0.1700
Data Index: 1620727 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.3231. Min Act: -0.1700
Data Index: 284227 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.3231. Min Act: -0.1700
Data Index: 2698067 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.3231. Min Act: -0.1700
Data Index: 5460069 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.3231. Min Act: -0.1700
Data Index: 2857048 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.2919. Min Act: -0.1700
Data Index: 7498167 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.2919. Min Act: -0.1700
Data Index: 3844122 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.2919. Min Act: -0.1700
Data Index: 7093777 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.2919. Min Act: -0.1700
Data Index: 994549 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.2919. Min Act: -0.1700
Data Index: 1159130 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.2606. Min Act: -0.1700
Data Index: 540219 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0106. Min Range: -7.0106
Max Act: 6.2919. Min Act: -0.1700
Data Index: 5370363 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19