Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2488 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3555. Min Range: -7.3555
Max Act: 7.3555. Min Act: -0.1700
Data Index: 838117 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3555. Min Range: -7.3555
Max Act: 7.3242. Min Act: -0.1700
Data Index: 4943620 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3555. Min Range: -7.3555
Max Act: 7.1055. Min Act: -0.1700
Data Index: 8825423 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3555. Min Range: -7.3555
Max Act: 7.0430. Min Act: -0.1700
Data Index: 208539 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.9805. Min Act: -0.1700
Data Index: 981703 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.9492. Min Act: -0.1700
Data Index: 7811891 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.9180. Min Act: -0.1700
Data Index: 5572909 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.8555. Min Act: -0.1700
Data Index: 7054861 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.7930. Min Act: -0.1700
Data Index: 6775890 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.8242. Min Act: -0.1700
Data Index: 5112728 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.7930. Min Act: -0.1700
Data Index: 829708 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.7930. Min Act: -0.1700
Data Index: 6999448 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.7930. Min Act: -0.1700
Data Index: 652141 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.7617. Min Act: -0.1700
Data Index: 6603948 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.7617. Min Act: -0.1700
Data Index: 7204613 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.7617. Min Act: -0.1700
Data Index: 3844914 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.7305. Min Act: -0.1700
Data Index: 3039658 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.6992. Min Act: -0.1700
Data Index: 4787629 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.6992. Min Act: -0.1700
Data Index: 3512997 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3555. Min Range: -7.3555
Max Act: 6.6992. Min Act: -0.1700
Data Index: 6082643 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19