Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1062. Min Range: -5.1062
Max Act: 5.1062. Min Act: -0.1700
Data Index: 7477262 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1062. Min Range: -5.1062
Max Act: 5.0437. Min Act: -0.1700
Data Index: 4399249 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1062. Min Range: -5.1062
Max Act: 5.0124. Min Act: -0.1700
Data Index: 6482436 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.9812. Min Act: -0.1700
Data Index: 669680 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.9187. Min Act: -0.1700
Data Index: 1471396 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.8874. Min Act: -0.1700
Data Index: 967741 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.9187. Min Act: -0.1700
Data Index: 3174237 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.8874. Min Act: -0.1700
Data Index: 8187688 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.8874. Min Act: -0.1700
Data Index: 85220 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.8562. Min Act: -0.1700
Data Index: 7850876 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.8874. Min Act: -0.1700
Data Index: 2290407 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.8562. Min Act: -0.1700
Data Index: 4417221 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.7937. Min Act: -0.1700
Data Index: 7055979 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.8249. Min Act: -0.1700
Data Index: 1502639 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.7937. Min Act: -0.1700
Data Index: 4543196 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.7937. Min Act: -0.1700
Data Index: 295959 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.7937. Min Act: -0.1700
Data Index: 538463 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.7937. Min Act: -0.1700
Data Index: 6040783 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.7624. Min Act: -0.1700
Data Index: 2817367 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1062. Min Range: -5.1062
Max Act: 4.7937. Min Act: -0.1700
Data Index: 961544 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19