Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3845. Min Range: -6.3845
Max Act: 6.3845. Min Act: -0.1700
Data Index: 8241469 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3845. Min Range: -6.3845
Max Act: 6.0095. Min Act: -0.1700
Data Index: 5956016 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.9470. Min Act: -0.1700
Data Index: 6002790 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8845. Min Act: -0.1700
Data Index: 7250847 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8845. Min Act: -0.1700
Data Index: 1316635 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8845. Min Act: -0.1700
Data Index: 7231305 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8220. Min Act: -0.1700
Data Index: 2109039 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8533. Min Act: -0.1700
Data Index: 1865785 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8220. Min Act: -0.1700
Data Index: 6140341 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8220. Min Act: -0.1700
Data Index: 7201878 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8220. Min Act: -0.1700
Data Index: 4781127 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.8220. Min Act: -0.1700
Data Index: 6077395 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.7908. Min Act: -0.1700
Data Index: 607098 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.7908. Min Act: -0.1700
Data Index: 1568176 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.7908. Min Act: -0.1700
Data Index: 4430458 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.7908. Min Act: -0.1700
Data Index: 3263547 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.7908. Min Act: -0.1700
Data Index: 1292305 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.7908. Min Act: -0.1700
Data Index: 1591727 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.7595. Min Act: -0.1700
Data Index: 3157873 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3845. Min Range: -6.3845
Max Act: 5.7595. Min Act: -0.1700
Data Index: 7046015 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19