Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1348 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0492. Min Range: -6.0492
Max Act: 6.0492. Min Act: -0.1700
Data Index: 4511227 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.9867. Min Act: -0.1700
Data Index: 4061526 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.9555. Min Act: -0.1700
Data Index: 5235394 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.9242. Min Act: -0.1700
Data Index: 7088889 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8930. Min Act: -0.1700
Data Index: 6454534 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8617. Min Act: -0.1700
Data Index: 4156055 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8617. Min Act: -0.1700
Data Index: 4391039 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8617. Min Act: -0.1700
Data Index: 4835093 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 6487061 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 5825048 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 6677877 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 6463747 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7992. Min Act: -0.1700
Data Index: 111676 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.8305. Min Act: -0.1700
Data Index: 1824508 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7992. Min Act: -0.1700
Data Index: 1247839 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7680. Min Act: -0.1700
Data Index: 7546470 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7367. Min Act: -0.1700
Data Index: 4535500 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7367. Min Act: -0.1700
Data Index: 3781851 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7055. Min Act: -0.1700
Data Index: 1553895 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0492. Min Range: -6.0492
Max Act: 5.7055. Min Act: -0.1700
Data Index: 7459383 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19