Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.7331. Min Act: -0.1700
Data Index: 2903663 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.6706. Min Act: -0.1700
Data Index: 8748072 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.4206. Min Act: -0.1700
Data Index: 6734803 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.3581. Min Act: -0.1700
Data Index: 812591 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.2331. Min Act: -0.1700
Data Index: 3510212 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.1706. Min Act: -0.1700
Data Index: 5119823 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.1081. Min Act: -0.1700
Data Index: 232438 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.0456. Min Act: -0.1700
Data Index: 3945771 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.0144. Min Act: -0.1700
Data Index: 2880648 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.0144. Min Act: -0.1700
Data Index: 3168810 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7331. Min Range: -6.7331
Max Act: 6.0144. Min Act: -0.1700
Data Index: 260297 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8783506 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.9831. Min Act: -0.1700
Data Index: 5134892 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.9519. Min Act: -0.1700
Data Index: 5462956 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.9519. Min Act: -0.1700
Data Index: 4771491 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.9519. Min Act: -0.1700
Data Index: 232533 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.9519. Min Act: -0.1700
Data Index: 6587352 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.9519. Min Act: -0.1700
Data Index: 922428 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.8894. Min Act: -0.1700
Data Index: 7439661 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7331. Min Range: -6.7331
Max Act: 5.9206. Min Act: -0.1700
Data Index: 6057539 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19