Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1001. Min Range: -6.1001
Max Act: 6.1001. Min Act: -0.1700
Data Index: 7658444 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1001. Min Range: -6.1001
Max Act: 6.0376. Min Act: -0.1700
Data Index: 6236014 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.9439. Min Act: -0.1700
Data Index: 3042775 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.8189. Min Act: -0.1700
Data Index: 4843932 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.8501. Min Act: -0.1700
Data Index: 6852198 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.8189. Min Act: -0.1700
Data Index: 3749163 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.7876. Min Act: -0.1700
Data Index: 6709103 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.8189. Min Act: -0.1700
Data Index: 8439970 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.8189. Min Act: -0.1700
Data Index: 4820035 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.8189. Min Act: -0.1700
Data Index: 1651375 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.8189. Min Act: -0.1700
Data Index: 7085818 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.7876. Min Act: -0.1700
Data Index: 707767 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.7876. Min Act: -0.1700
Data Index: 1931984 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.7564. Min Act: -0.1700
Data Index: 4820037 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.7251. Min Act: -0.1700
Data Index: 4496694 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.7564. Min Act: -0.1700
Data Index: 7140103 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.7564. Min Act: -0.1700
Data Index: 54599 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.6939. Min Act: -0.1700
Data Index: 6822249 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.6939. Min Act: -0.1700
Data Index: 1884827 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1001. Min Range: -6.1001
Max Act: 5.7251. Min Act: -0.1700
Data Index: 6307595 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19