Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 882 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.8732. Min Act: -0.1700
Data Index: 1835670 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.7481. Min Act: -0.1700
Data Index: 4194185 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.7168. Min Act: -0.1700
Data Index: 7625445 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.7168. Min Act: -0.1700
Data Index: 7407466 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.7168. Min Act: -0.1700
Data Index: 8808686 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 6181894 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 7611263 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6855. Min Act: -0.1700
Data Index: 7434676 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6855. Min Act: -0.1700
Data Index: 2141127 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 6209464 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 8418216 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 121868 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6855. Min Act: -0.1700
Data Index: 457469 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 3443803 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 7703316 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 4492718 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6542. Min Act: -0.1700
Data Index: 2359465 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6855. Min Act: -0.1700
Data Index: 5231516 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6229. Min Act: -0.1700
Data Index: 1489353 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8732. Min Range: -3.8732
Max Act: 3.6229. Min Act: -0.1700
Data Index: 3894510 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19