Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 244 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0604. Min Range: -8.0604
Max Act: 8.0604. Min Act: -0.1700
Data Index: 4575353 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.4979. Min Act: -0.1700
Data Index: 400045 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.4354. Min Act: -0.1700
Data Index: 8699346 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.4354. Min Act: -0.1700
Data Index: 1613998 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.3729. Min Act: -0.1700
Data Index: 328374 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.3729. Min Act: -0.1700
Data Index: 8757123 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.4042. Min Act: -0.1700
Data Index: 7745507 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.3729. Min Act: -0.1700
Data Index: 4795477 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.3729. Min Act: -0.1700
Data Index: 3790123 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.3729. Min Act: -0.1700
Data Index: 1390561 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.3104. Min Act: -0.1700
Data Index: 3572847 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2792. Min Act: -0.1700
Data Index: 5890638 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2792. Min Act: -0.1700
Data Index: 3831273 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2479. Min Act: -0.1700
Data Index: 7880499 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2479. Min Act: -0.1700
Data Index: 1054388 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2479. Min Act: -0.1700
Data Index: 6519157 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2792. Min Act: -0.1700
Data Index: 2941831 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2479. Min Act: -0.1700
Data Index: 2755315 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2167. Min Act: -0.1700
Data Index: 2720189 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0604. Min Range: -8.0604
Max Act: 7.2167. Min Act: -0.1700
Data Index: 7202521 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19