Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1335. Min Range: -6.1335
Max Act: 6.1335. Min Act: -0.1700
Data Index: 2738154 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1335. Min Range: -6.1335
Max Act: 6.1335. Min Act: -0.1700
Data Index: 8294634 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1335. Min Range: -6.1335
Max Act: 6.0085. Min Act: -0.1700
Data Index: 2925015 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.9772. Min Act: -0.1700
Data Index: 8163897 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.9772. Min Act: -0.1700
Data Index: 8585632 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.9460. Min Act: -0.1700
Data Index: 5667242 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.9147. Min Act: -0.1700
Data Index: 2338520 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.9147. Min Act: -0.1700
Data Index: 1590782 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 2473188 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 3343085 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 3781329 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 5642216 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 2659326 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8835. Min Act: -0.1700
Data Index: 427115 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8210. Min Act: -0.1700
Data Index: 8636803 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8522. Min Act: -0.1700
Data Index: 5139543 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8522. Min Act: -0.1700
Data Index: 1361100 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8522. Min Act: -0.1700
Data Index: 3742395 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8210. Min Act: -0.1700
Data Index: 3845514 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1335. Min Range: -6.1335
Max Act: 5.8210. Min Act: -0.1700
Data Index: 2870536 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19