Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4445 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0003. Min Range: -8.0003
Max Act: 8.0003. Min Act: -0.1700
Data Index: 656230 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.8440. Min Act: -0.1700
Data Index: 3888003 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.8440. Min Act: -0.1700
Data Index: 7150672 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.7815. Min Act: -0.1700
Data Index: 1617396 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.8128. Min Act: -0.1700
Data Index: 5378159 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.7503. Min Act: -0.1700
Data Index: 8291160 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.7190. Min Act: -0.1700
Data Index: 6523617 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.6565. Min Act: -0.1700
Data Index: 7848997 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.5940. Min Act: -0.1700
Data Index: 2875940 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.6253. Min Act: -0.1700
Data Index: 8295089 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.6253. Min Act: -0.1700
Data Index: 1233188 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.6253. Min Act: -0.1700
Data Index: 2213134 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.6253. Min Act: -0.1700
Data Index: 6396958 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.5940. Min Act: -0.1700
Data Index: 3933065 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.5940. Min Act: -0.1700
Data Index: 1882937 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.6253. Min Act: -0.1700
Data Index: 4881828 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.6253. Min Act: -0.1700
Data Index: 644845 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.5940. Min Act: -0.1700
Data Index: 7672709 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.5940. Min Act: -0.1700
Data Index: 2085156 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0003. Min Range: -8.0003
Max Act: 7.5940. Min Act: -0.1700
Data Index: 5303817 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19