Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6349 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6510. Min Range: -9.6510
Max Act: 9.6510. Min Act: -0.1700
Data Index: 2113216 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6510. Min Range: -9.6510
Max Act: 9.2135. Min Act: -0.1700
Data Index: 7494713 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6510. Min Range: -9.6510
Max Act: 9.2760. Min Act: -0.1700
Data Index: 3457099 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6510. Min Range: -9.6510
Max Act: 9.1510. Min Act: -0.1700
Data Index: 5935406 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.9635. Min Act: -0.1700
Data Index: 6398651 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.9635. Min Act: -0.1700
Data Index: 5842865 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.9010. Min Act: -0.1700
Data Index: 918333 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.8385. Min Act: -0.1700
Data Index: 1113440 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.8385. Min Act: -0.1700
Data Index: 30061 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.8385. Min Act: -0.1700
Data Index: 8096467 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.7135. Min Act: -0.1700
Data Index: 2490512 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.7760. Min Act: -0.1700
Data Index: 5857589 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.7760. Min Act: -0.1700
Data Index: 838789 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.7760. Min Act: -0.1700
Data Index: 1066652 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.7135. Min Act: -0.1700
Data Index: 6398652 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.7135. Min Act: -0.1700
Data Index: 5748647 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.7135. Min Act: -0.1700
Data Index: 994313 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.7135. Min Act: -0.1700
Data Index: 7202550 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.6510. Min Act: -0.1700
Data Index: 5301140 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6510. Min Range: -9.6510
Max Act: 8.6510. Min Act: -0.1700
Data Index: 2497258 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19