Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4512 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5043. Min Range: -8.5043
Max Act: 8.5043. Min Act: -0.1700
Data Index: 1882554 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5043. Min Range: -8.5043
Max Act: 8.5043. Min Act: -0.1700
Data Index: 199361 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.8168. Min Act: -0.1700
Data Index: 8206531 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.8168. Min Act: -0.1700
Data Index: 4702413 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.7543. Min Act: -0.1700
Data Index: 152911 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.7543. Min Act: -0.1700
Data Index: 6405728 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.7231. Min Act: -0.1700
Data Index: 6163075 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.7231. Min Act: -0.1700
Data Index: 2406693 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.6918. Min Act: -0.1700
Data Index: 2889029 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.6918. Min Act: -0.1700
Data Index: 1769386 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.6606. Min Act: -0.1700
Data Index: 4115413 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.6293. Min Act: -0.1700
Data Index: 1338274 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.6293. Min Act: -0.1700
Data Index: 6439946 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.6293. Min Act: -0.1700
Data Index: 709962 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.6293. Min Act: -0.1700
Data Index: 2537422 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.5981. Min Act: -0.1700
Data Index: 8199455 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.5668. Min Act: -0.1700
Data Index: 2858730 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.5668. Min Act: -0.1700
Data Index: 1574556 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.5356. Min Act: -0.1700
Data Index: 5917761 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5043. Min Range: -8.5043
Max Act: 7.5668. Min Act: -0.1700
Data Index: 4682179 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19