Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.6018. Min Act: -0.1700
Data Index: 5678736 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.5392. Min Act: -0.1700
Data Index: 8163053 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.5705. Min Act: -0.1700
Data Index: 5169096 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.5392. Min Act: -0.1700
Data Index: 2458690 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.5079. Min Act: -0.1700
Data Index: 7621303 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.5079. Min Act: -0.1700
Data Index: 2659413 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.5079. Min Act: -0.1700
Data Index: 3290669 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4922. Min Act: -0.1700
Data Index: 2644026 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4922. Min Act: -0.1700
Data Index: 2635354 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4922. Min Act: -0.1700
Data Index: 5138988 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4766. Min Act: -0.1700
Data Index: 6985632 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4609. Min Act: -0.1700
Data Index: 4763070 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4766. Min Act: -0.1700
Data Index: 2480901 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4609. Min Act: -0.1700
Data Index: 1765614 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4609. Min Act: -0.1700
Data Index: 8724519 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4609. Min Act: -0.1700
Data Index: 5776803 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4609. Min Act: -0.1700
Data Index: 2504533 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4452. Min Act: -0.1700
Data Index: 2635353 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4452. Min Act: -0.1700
Data Index: 3406196 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6018. Min Range: -3.6018
Max Act: 3.4452. Min Act: -0.1700
Data Index: 5932422 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19