Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 939 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.3438. Min Act: -0.1700
Data Index: 3723802 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.2967. Min Act: -0.1700
Data Index: 6501636 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.2653. Min Act: -0.1700
Data Index: 7327786 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.2339. Min Act: -0.1700
Data Index: 664406 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.1553. Min Act: -0.1700
Data Index: 5999046 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.1710. Min Act: -0.1700
Data Index: 6207130 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0765. Min Act: -0.1700
Data Index: 7224759 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0765. Min Act: -0.1700
Data Index: 5433155 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0449. Min Act: -0.1700
Data Index: 5946261 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0291. Min Act: -0.1700
Data Index: 4681921 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0449. Min Act: -0.1700
Data Index: 6818207 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0134. Min Act: -0.1700
Data Index: 6009829 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9817. Min Act: -0.1700
Data Index: 1603261 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0134. Min Act: -0.1700
Data Index: 5185885 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0291. Min Act: -0.1700
Data Index: 7200481 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9975. Min Act: -0.1700
Data Index: 5770263 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9817. Min Act: -0.1700
Data Index: 1351576 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9817. Min Act: -0.1700
Data Index: 1054029 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9817. Min Act: -0.1700
Data Index: 6665616 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9817. Min Act: -0.1700
Data Index: 5331338 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19