Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.1070. Min Act: -0.1700
Data Index: 5994207 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.1070. Min Act: -0.1700
Data Index: 4623277 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0755. Min Act: -0.1700
Data Index: 5669014 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0755. Min Act: -0.1700
Data Index: 1797550 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0755. Min Act: -0.1700
Data Index: 1641194 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0755. Min Act: -0.1700
Data Index: 1537200 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0755. Min Act: -0.1700
Data Index: 4632086 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 4488446 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0755. Min Act: -0.1700
Data Index: 2399475 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0755. Min Act: -0.1700
Data Index: 8692805 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 2547616 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 4401438 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 291933 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 1297705 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 2982078 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0123. Min Act: -0.1700
Data Index: 1401086 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 986184 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 5057633 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0755. Min Act: -0.1700
Data Index: 3047324 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1070. Min Range: -3.1070
Max Act: 3.0439. Min Act: -0.1700
Data Index: 3235856 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19