Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.4172. Min Act: -0.1700
Data Index: 1952289 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.3547. Min Act: -0.1700
Data Index: 3055018 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.2922. Min Act: -0.1700
Data Index: 1226546 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.2609. Min Act: -0.1700
Data Index: 5636157 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1984. Min Act: -0.1700
Data Index: 7262553 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1984. Min Act: -0.1700
Data Index: 5276263 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1984. Min Act: -0.1700
Data Index: 8285526 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1984. Min Act: -0.1700
Data Index: 732088 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1984. Min Act: -0.1700
Data Index: 7183657 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1672. Min Act: -0.1700
Data Index: 861623 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1672. Min Act: -0.1700
Data Index: 285669 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1984. Min Act: -0.1700
Data Index: 128910 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1672. Min Act: -0.1700
Data Index: 7400589 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1672. Min Act: -0.1700
Data Index: 4801169 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1359. Min Act: -0.1700
Data Index: 4647410 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1047. Min Act: -0.1700
Data Index: 4647414 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1047. Min Act: -0.1700
Data Index: 732087 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1047. Min Act: -0.1700
Data Index: 6896242 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1047. Min Act: -0.1700
Data Index: 7400585 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4172. Min Range: -5.4172
Max Act: 5.1047. Min Act: -0.1700
Data Index: 7145799 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19