Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2320 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1021. Min Range: -6.1021
Max Act: 6.1021. Min Act: -0.1700
Data Index: 317133 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1021. Min Range: -6.1021
Max Act: 6.0083. Min Act: -0.1700
Data Index: 3782031 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.6021. Min Act: -0.1700
Data Index: 5993263 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.6021. Min Act: -0.1700
Data Index: 1991503 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.5708. Min Act: -0.1700
Data Index: 5008481 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.5708. Min Act: -0.1700
Data Index: 8284266 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.5396. Min Act: -0.1700
Data Index: 1803164 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.5396. Min Act: -0.1700
Data Index: 792412 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.4771. Min Act: -0.1700
Data Index: 7285789 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.4458. Min Act: -0.1700
Data Index: 1367617 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.4458. Min Act: -0.1700
Data Index: 8003868 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.4458. Min Act: -0.1700
Data Index: 7285791 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.4146. Min Act: -0.1700
Data Index: 2552597 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.3833. Min Act: -0.1700
Data Index: 4147481 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.4146. Min Act: -0.1700
Data Index: 6654667 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.4146. Min Act: -0.1700
Data Index: 7543156 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.4146. Min Act: -0.1700
Data Index: 7134343 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.3833. Min Act: -0.1700
Data Index: 778313 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.3833. Min Act: -0.1700
Data Index: 7863513 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1021. Min Range: -6.1021
Max Act: 5.3833. Min Act: -0.1700
Data Index: 7642919 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19