Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3712 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0159. Min Range: -5.0159
Max Act: 5.0159. Min Act: -0.1700
Data Index: 5549237 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.9221. Min Act: -0.1700
Data Index: 6720675 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8909. Min Act: -0.1700
Data Index: 1427691 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.9534. Min Act: -0.1700
Data Index: 2329732 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8909. Min Act: -0.1700
Data Index: 1611114 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8909. Min Act: -0.1700
Data Index: 1585296 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8909. Min Act: -0.1700
Data Index: 4814030 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8909. Min Act: -0.1700
Data Index: 4067984 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8596. Min Act: -0.1700
Data Index: 2274782 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8596. Min Act: -0.1700
Data Index: 2834756 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8284. Min Act: -0.1700
Data Index: 3862142 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8909. Min Act: -0.1700
Data Index: 2741991 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8596. Min Act: -0.1700
Data Index: 3409918 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8284. Min Act: -0.1700
Data Index: 4285945 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8284. Min Act: -0.1700
Data Index: 3089932 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8284. Min Act: -0.1700
Data Index: 5501343 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8284. Min Act: -0.1700
Data Index: 852912 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8284. Min Act: -0.1700
Data Index: 3164155 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8284. Min Act: -0.1700
Data Index: 643825 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0159. Min Range: -5.0159
Max Act: 4.8284. Min Act: -0.1700
Data Index: 5737460 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19