Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6272 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.5904. Min Act: -0.1700
Data Index: 5579606 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.5278. Min Act: -0.1700
Data Index: 763760 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.5278. Min Act: -0.1700
Data Index: 7584246 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.5278. Min Act: -0.1700
Data Index: 8735110 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.5278. Min Act: -0.1700
Data Index: 8128790 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4964. Min Act: -0.1700
Data Index: 3276829 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4964. Min Act: -0.1700
Data Index: 4892589 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4964. Min Act: -0.1700
Data Index: 3891517 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4964. Min Act: -0.1700
Data Index: 3282330 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4964. Min Act: -0.1700
Data Index: 5654793 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 6585611 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 7175005 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 7495126 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 1814288 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4338. Min Act: -0.1700
Data Index: 3490119 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 2677932 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 5879744 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 1145229 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 3564352 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5904. Min Range: -3.5904
Max Act: 3.4651. Min Act: -0.1700
Data Index: 5090332 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19