Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.9426. Min Act: -0.1700
Data Index: 2513841 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.8176. Min Act: -0.1700
Data Index: 8253263 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.7551. Min Act: -0.1700
Data Index: 5516861 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.6301. Min Act: -0.1700
Data Index: 2841938 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.6301. Min Act: -0.1700
Data Index: 969029 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.5988. Min Act: -0.1700
Data Index: 748594 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.5051. Min Act: -0.1700
Data Index: 4342647 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.4426. Min Act: -0.1700
Data Index: 417703 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.4113. Min Act: -0.1700
Data Index: 576240 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.4113. Min Act: -0.1700
Data Index: 2921834 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3801. Min Act: -0.1700
Data Index: 53507 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3801. Min Act: -0.1700
Data Index: 4574408 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3801. Min Act: -0.1700
Data Index: 4647934 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3488. Min Act: -0.1700
Data Index: 8494726 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3801. Min Act: -0.1700
Data Index: 611802 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3488. Min Act: -0.1700
Data Index: 3495571 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3488. Min Act: -0.1700
Data Index: 4411147 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3488. Min Act: -0.1700
Data Index: 8827954 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3176. Min Act: -0.1700
Data Index: 7718124 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9426. Min Range: -7.9426
Max Act: 7.3176. Min Act: -0.1700
Data Index: 6605572 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19