Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5118 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.9998. Min Act: -0.1700
Data Index: 3802617 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.9150. Min Act: -0.1700
Data Index: 8415100 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.9150. Min Act: -0.1700
Data Index: 7095070 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.9150. Min Act: -0.1700
Data Index: 1824541 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.9150. Min Act: -0.1700
Data Index: 1477532 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8980. Min Act: -0.1700
Data Index: 7162322 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8980. Min Act: -0.1700
Data Index: 3176913 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8980. Min Act: -0.1700
Data Index: 2686278 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8638. Min Act: -0.1700
Data Index: 7165238 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8638. Min Act: -0.1700
Data Index: 6741980 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8809. Min Act: -0.1700
Data Index: 6089063 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8980. Min Act: -0.1700
Data Index: 5700566 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8809. Min Act: -0.1700
Data Index: 5549319 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8809. Min Act: -0.1700
Data Index: 2186544 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8638. Min Act: -0.1700
Data Index: 6462184 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8638. Min Act: -0.1700
Data Index: 3755222 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8467. Min Act: -0.1700
Data Index: 3386012 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8638. Min Act: -0.1700
Data Index: 1783069 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8638. Min Act: -0.1700
Data Index: 4943016 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9998. Min Range: -1.9998
Max Act: 1.8638. Min Act: -0.1700
Data Index: 3316833 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19