Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 1968236 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 294610 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 6260831 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 6023574 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 7577054 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 4175175 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 6404865 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1677
Data Index: 4112779 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 7727434 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1699
Data Index: 5443372 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 8621879 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 3989489 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 4875763 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1621. Min Act: -0.1700
Data Index: 3536377 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1454. Min Act: -0.1700
Data Index: 7787934 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1287. Min Act: -0.1700
Data Index: 7237449 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1120. Min Act: -0.1700
Data Index: 1374636 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1120. Min Act: -0.1700
Data Index: 8171819 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1120. Min Act: -0.1700
Data Index: 4770499 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1621. Min Range: -2.1621
Max Act: 2.1120. Min Act: -0.1700
Data Index: 7828869 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19