Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2106 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1963. Min Act: -0.1700
Data Index: 2341768 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1650. Min Act: -0.1700
Data Index: 2518331 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1338. Min Act: -0.1700
Data Index: 7360601 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1338. Min Act: -0.1700
Data Index: 69522 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1025. Min Act: -0.1700
Data Index: 786469 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1025. Min Act: -0.1700
Data Index: 4514350 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1025. Min Act: -0.1700
Data Index: 724244 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1025. Min Act: -0.1700
Data Index: 216323 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1025. Min Act: -0.1700
Data Index: 176347 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1025. Min Act: -0.1700
Data Index: 3643087 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.1025. Min Act: -0.1700
Data Index: 7030932 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0713. Min Act: -0.1700
Data Index: 2687502 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0713. Min Act: -0.1700
Data Index: 7092072 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0400. Min Act: -0.1700
Data Index: 1549961 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0400. Min Act: -0.1700
Data Index: 6930159 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0400. Min Act: -0.1700
Data Index: 6799957 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0713. Min Act: -0.1700
Data Index: 5006520 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0713. Min Act: -0.1700
Data Index: 1034450 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0713. Min Act: -0.1700
Data Index: 5853030 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1963. Min Range: -5.1963
Max Act: 5.0713. Min Act: -0.1700
Data Index: 5319001 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19