Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2141. Min Range: -4.2141
Max Act: 4.2141. Min Act: -0.1700
Data Index: 7475216 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2141. Min Range: -4.2141
Max Act: 4.1203. Min Act: -0.1700
Data Index: 5436804 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2141. Min Range: -4.2141
Max Act: 4.1203. Min Act: -0.1700
Data Index: 4434650 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2141. Min Range: -4.2141
Max Act: 4.0578. Min Act: -0.1700
Data Index: 6115010 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2141. Min Range: -4.2141
Max Act: 4.0265. Min Act: -0.1700
Data Index: 3895108 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2141. Min Range: -4.2141
Max Act: 4.0265. Min Act: -0.1700
Data Index: 1037536 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9953. Min Act: -0.1700
Data Index: 1012005 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9953. Min Act: -0.1700
Data Index: 1037537 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9953. Min Act: -0.1700
Data Index: 4068352 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9640. Min Act: -0.1700
Data Index: 2160576 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9640. Min Act: -0.1700
Data Index: 8118705 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9640. Min Act: -0.1700
Data Index: 7889528 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9640. Min Act: -0.1700
Data Index: 2915901 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9953. Min Act: -0.1700
Data Index: 832534 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9640. Min Act: -0.1700
Data Index: 5443874 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9640. Min Act: -0.1700
Data Index: 3355053 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9640. Min Act: -0.1700
Data Index: 4473039 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9327. Min Act: -0.1700
Data Index: 4448247 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9327. Min Act: -0.1700
Data Index: 1301564 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2141. Min Range: -4.2141
Max Act: 3.9327. Min Act: -0.1700
Data Index: 3211642 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19