Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1945 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2270. Min Range: -6.2270
Max Act: 6.2270. Min Act: -0.1700
Data Index: 5680857 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2270. Min Range: -6.2270
Max Act: 6.1332. Min Act: -0.1700
Data Index: 8214944 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2270. Min Range: -6.2270
Max Act: 6.1332. Min Act: -0.1700
Data Index: 1853096 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2270. Min Range: -6.2270
Max Act: 6.0707. Min Act: -0.1700
Data Index: 5004583 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2270. Min Range: -6.2270
Max Act: 6.1020. Min Act: -0.1700
Data Index: 1160507 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2270. Min Range: -6.2270
Max Act: 6.0707. Min Act: -0.1700
Data Index: 2459464 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2270. Min Range: -6.2270
Max Act: 6.0082. Min Act: -0.1700
Data Index: 4215542 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.9770. Min Act: -0.1700
Data Index: 5478403 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.9457. Min Act: -0.1700
Data Index: 3156179 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.9457. Min Act: -0.1700
Data Index: 2604506 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8520. Min Act: -0.1700
Data Index: 7721643 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8832. Min Act: -0.1700
Data Index: 1725047 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8832. Min Act: -0.1700
Data Index: 1824365 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8832. Min Act: -0.1700
Data Index: 3752675 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8520. Min Act: -0.1700
Data Index: 2765072 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8520. Min Act: -0.1700
Data Index: 5859202 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8207. Min Act: -0.1700
Data Index: 2020116 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8207. Min Act: -0.1700
Data Index: 2894317 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8207. Min Act: -0.1700
Data Index: 2143124 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2270. Min Range: -6.2270
Max Act: 5.8207. Min Act: -0.1700
Data Index: 4785247 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19