Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0668. Min Range: -7.0668
Max Act: 7.0668. Min Act: -0.1700
Data Index: 6634704 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.8480. Min Act: -0.1700
Data Index: 533482 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.7855. Min Act: -0.1700
Data Index: 3168269 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.7855. Min Act: -0.1700
Data Index: 6534430 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.6605. Min Act: -0.1700
Data Index: 8693055 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.6293. Min Act: -0.1700
Data Index: 2682499 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.6605. Min Act: -0.1700
Data Index: 5921805 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.5668. Min Act: -0.1700
Data Index: 5988156 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.5355. Min Act: -0.1700
Data Index: 1323728 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.5043. Min Act: -0.1700
Data Index: 1109825 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.5043. Min Act: -0.1700
Data Index: 533487 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4730. Min Act: -0.1700
Data Index: 3984806 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4730. Min Act: -0.1700
Data Index: 7130304 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4730. Min Act: -0.1700
Data Index: 5191356 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4418. Min Act: -0.1700
Data Index: 726216 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4418. Min Act: -0.1700
Data Index: 6046110 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4418. Min Act: -0.1700
Data Index: 3654395 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4418. Min Act: -0.1700
Data Index: 5665793 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4105. Min Act: -0.1700
Data Index: 5838452 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0668. Min Range: -7.0668
Max Act: 6.4105. Min Act: -0.1700
Data Index: 3464025 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19