Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.2114. Min Act: -0.1700
Data Index: 6685748 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.1801. Min Act: -0.1700
Data Index: 5417867 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.1176. Min Act: -0.1700
Data Index: 8276135 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0551. Min Act: -0.1700
Data Index: 8812421 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 79463 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9926. Min Act: -0.1700
Data Index: 7550306 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9926. Min Act: -0.1700
Data Index: 1268224 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9926. Min Act: -0.1700
Data Index: 1385542 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9614. Min Act: -0.1700
Data Index: 784286 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9301. Min Act: -0.1700
Data Index: 344417 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8989. Min Act: -0.1700
Data Index: 3837818 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8676. Min Act: -0.1700
Data Index: 4165581 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8364. Min Act: -0.1700
Data Index: 1058509 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8364. Min Act: -0.1700
Data Index: 167351 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8364. Min Act: -0.1700
Data Index: 5791656 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8364. Min Act: -0.1700
Data Index: 3884042 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8676. Min Act: -0.1700
Data Index: 2143938 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8364. Min Act: -0.1700
Data Index: 5268647 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8051. Min Act: -0.1700
Data Index: 3133495 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8051. Min Act: -0.1700
Data Index: 5553839 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19