Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.7963. Min Act: -0.1700
Data Index: 7334183 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.7963. Min Act: -0.1700
Data Index: 7644439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.7024. Min Act: -0.1700
Data Index: 8229560 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6711. Min Act: -0.1700
Data Index: 6367127 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6711. Min Act: -0.1700
Data Index: 7051552 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6711. Min Act: -0.1700
Data Index: 6355944 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6711. Min Act: -0.1700
Data Index: 8347638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6711. Min Act: -0.1700
Data Index: 5496017 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6398. Min Act: -0.1700
Data Index: 6815000 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6398. Min Act: -0.1700
Data Index: 498067 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6398. Min Act: -0.1700
Data Index: 2624424 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6398. Min Act: -0.1700
Data Index: 8140896 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6398. Min Act: -0.1700
Data Index: 7908198 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6398. Min Act: -0.1700
Data Index: 4663395 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6398. Min Act: -0.1700
Data Index: 7121277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6086. Min Act: -0.1700
Data Index: 5832694 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6086. Min Act: -0.1700
Data Index: 3002934 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6086. Min Act: -0.1700
Data Index: 5869865 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6086. Min Act: -0.1700
Data Index: 1123294 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7963. Min Range: -3.7963
Max Act: 3.6086. Min Act: -0.1700
Data Index: 256062 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19