Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.8064. Min Act: -0.1700
Data Index: 249865 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.7127. Min Act: -0.1700
Data Index: 1760276 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.6814. Min Act: -0.1700
Data Index: 470038 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.5877. Min Act: -0.1700
Data Index: 1041884 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.4939. Min Act: -0.1700
Data Index: 4223010 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.4002. Min Act: -0.1700
Data Index: 4052880 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.3377. Min Act: -0.1700
Data Index: 3168698 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.3377. Min Act: -0.1700
Data Index: 7787321 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.3377. Min Act: -0.1700
Data Index: 3173305 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.3377. Min Act: -0.1700
Data Index: 1666867 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.3064. Min Act: -0.1700
Data Index: 8092409 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2752. Min Act: -0.1700
Data Index: 914556 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2752. Min Act: -0.1700
Data Index: 4693212 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2752. Min Act: -0.1700
Data Index: 3496045 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2127. Min Act: -0.1700
Data Index: 1767907 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2127. Min Act: -0.1700
Data Index: 2004638 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2439. Min Act: -0.1700
Data Index: 8493592 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2439. Min Act: -0.1700
Data Index: 1699337 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2127. Min Act: -0.1700
Data Index: 6859293 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8064. Min Range: -4.8064
Max Act: 4.2439. Min Act: -0.1700
Data Index: 4978410 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19