Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4920 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.5967. Min Act: -0.1700
Data Index: 8077879 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.5342. Min Act: -0.1700
Data Index: 1626967 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.4092. Min Act: -0.1700
Data Index: 1626965 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2529. Min Act: -0.1700
Data Index: 7438193 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2529. Min Act: -0.1700
Data Index: 4788175 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2217. Min Act: -0.1700
Data Index: 578924 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.1904. Min Act: -0.1700
Data Index: 7438195 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2217. Min Act: -0.1700
Data Index: 3776925 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2217. Min Act: -0.1700
Data Index: 819395 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2217. Min Act: -0.1700
Data Index: 5169522 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2217. Min Act: -0.1700
Data Index: 4470002 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2217. Min Act: -0.1700
Data Index: 8698097 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2529. Min Act: -0.1700
Data Index: 4020866 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2217. Min Act: -0.1700
Data Index: 7538893 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.2217. Min Act: -0.1700
Data Index: 5453944 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.1904. Min Act: -0.1700
Data Index: 3541442 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.1904. Min Act: -0.1700
Data Index: 241482 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.1904. Min Act: -0.1700
Data Index: 5270961 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.1591. Min Act: -0.1700
Data Index: 241483 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5967. Min Range: -4.5967
Max Act: 4.1904. Min Act: -0.1700
Data Index: 63881 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19