Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3982 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.4172. Min Act: -0.1700
Data Index: 5374948 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.3859. Min Act: -0.1700
Data Index: 8401887 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.3859. Min Act: -0.1700
Data Index: 2145254 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.3234. Min Act: -0.1700
Data Index: 1055855 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.3234. Min Act: -0.1700
Data Index: 2910743 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.2297. Min Act: -0.1700
Data Index: 1081317 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.1672. Min Act: -0.1700
Data Index: 7305707 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.1672. Min Act: -0.1700
Data Index: 6488618 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.1359. Min Act: -0.1700
Data Index: 4925918 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.1047. Min Act: -0.1700
Data Index: 308247 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.1047. Min Act: -0.1700
Data Index: 766250 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4172. Min Range: -6.4172
Max Act: 5.9797. Min Act: -0.1700
Data Index: 6942805 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4172. Min Range: -6.4172
Max Act: 6.0109. Min Act: -0.1700
Data Index: 8803921 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4172. Min Range: -6.4172
Max Act: 5.9797. Min Act: -0.1700
Data Index: 4884845 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4172. Min Range: -6.4172
Max Act: 5.9484. Min Act: -0.1700
Data Index: 6221571 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4172. Min Range: -6.4172
Max Act: 5.9484. Min Act: -0.1700
Data Index: 6981571 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4172. Min Range: -6.4172
Max Act: 5.9484. Min Act: -0.1700
Data Index: 8538212 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4172. Min Range: -6.4172
Max Act: 5.9484. Min Act: -0.1700
Data Index: 7256627 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4172. Min Range: -6.4172
Max Act: 5.9172. Min Act: -0.1700
Data Index: 5500391 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4172. Min Range: -6.4172
Max Act: 5.9172. Min Act: -0.1700
Data Index: 6301629 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19