Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3683 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9970. Min Act: -0.1700
Data Index: 4595884 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9631. Min Act: -0.1700
Data Index: 8544798 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9462. Min Act: -0.1700
Data Index: 1543820 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9631. Min Act: -0.1700
Data Index: 7952295 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9292. Min Act: -0.1700
Data Index: 355821 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9292. Min Act: -0.1700
Data Index: 6886960 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9292. Min Act: -0.1699
Data Index: 1805685 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9121. Min Act: -0.1686
Data Index: 1857032 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9292. Min Act: -0.1700
Data Index: 4813366 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.8951. Min Act: -0.1696
Data Index: 483054 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9121. Min Act: -0.1700
Data Index: 1556105 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9121. Min Act: -0.1700
Data Index: 1127373 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9121. Min Act: -0.1700
Data Index: 8235957 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.8951. Min Act: -0.1700
Data Index: 1047844 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9121. Min Act: -0.1700
Data Index: 6139790 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.8951. Min Act: -0.1700
Data Index: 1669395 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.8951. Min Act: -0.1700
Data Index: 5573149 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.8951. Min Act: -0.1700
Data Index: 7278831 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.9121. Min Act: -0.1700
Data Index: 3243727 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9970. Min Range: -1.9970
Max Act: 1.8951. Min Act: -0.1700
Data Index: 4728523 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19