Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2527 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.9142. Min Act: -0.1700
Data Index: 438331 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.7892. Min Act: -0.1700
Data Index: 698476 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.7892. Min Act: -0.1700
Data Index: 8743513 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.7580. Min Act: -0.1700
Data Index: 2917248 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.7267. Min Act: -0.1700
Data Index: 4192374 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.7267. Min Act: -0.1700
Data Index: 5931877 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.6642. Min Act: -0.1700
Data Index: 7805905 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.6642. Min Act: -0.1700
Data Index: 5850050 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.6642. Min Act: -0.1700
Data Index: 8114 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.6330. Min Act: -0.1700
Data Index: 8016382 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.6330. Min Act: -0.1700
Data Index: 8742171 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.6017. Min Act: -0.1700
Data Index: 8071801 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.5705. Min Act: -0.1700
Data Index: 703469 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.5705. Min Act: -0.1700
Data Index: 3559213 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.5705. Min Act: -0.1700
Data Index: 7323386 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.5392. Min Act: -0.1700
Data Index: 2695101 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.5392. Min Act: -0.1700
Data Index: 588879 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.5392. Min Act: -0.1700
Data Index: 2078370 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.5392. Min Act: -0.1700
Data Index: 898004 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9142. Min Range: -4.9142
Max Act: 4.5080. Min Act: -0.1700
Data Index: 4074547 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19