Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4747. Min Act: -0.1700
Data Index: 581594 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4434. Min Act: -0.1700
Data Index: 4603025 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4747. Min Act: -0.1700
Data Index: 7920001 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4434. Min Act: -0.1700
Data Index: 150244 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4434. Min Act: -0.1700
Data Index: 8472685 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4434. Min Act: -0.1700
Data Index: 3414642 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4122. Min Act: -0.1700
Data Index: 7765079 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4122. Min Act: -0.1700
Data Index: 2198445 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4434. Min Act: -0.1700
Data Index: 8068855 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3809. Min Act: -0.1700
Data Index: 1020666 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3809. Min Act: -0.1700
Data Index: 6098038 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3809. Min Act: -0.1700
Data Index: 8167945 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.4122. Min Act: -0.1700
Data Index: 6714701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3809. Min Act: -0.1700
Data Index: 5076019 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3809. Min Act: -0.1700
Data Index: 1392933 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3496. Min Act: -0.1700
Data Index: 671282 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3809. Min Act: -0.1700
Data Index: 6602784 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3496. Min Act: -0.1700
Data Index: 8581120 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3496. Min Act: -0.1700
Data Index: 2709799 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4747. Min Range: -4.4747
Max Act: 4.3496. Min Act: -0.1700
Data Index: 6097780 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19