Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2440 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.6595. Min Act: -0.1700
Data Index: 3105474 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.6439. Min Act: -0.1700
Data Index: 6403870 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.6595. Min Act: -0.1700
Data Index: 3708632 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.6282. Min Act: -0.1700
Data Index: 4653768 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.6126. Min Act: -0.1700
Data Index: 2231481 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5969. Min Act: -0.1700
Data Index: 6750134 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5969. Min Act: -0.1700
Data Index: 7907664 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5969. Min Act: -0.1700
Data Index: 6956509 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5813. Min Act: -0.1700
Data Index: 6438382 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5813. Min Act: -0.1700
Data Index: 5121629 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5813. Min Act: -0.1700
Data Index: 4995154 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5813. Min Act: -0.1700
Data Index: 4531577 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5813. Min Act: -0.1700
Data Index: 999115 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5656. Min Act: -0.1700
Data Index: 3888943 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5813. Min Act: -0.1700
Data Index: 674254 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5500. Min Act: -0.1700
Data Index: 6393291 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5500. Min Act: -0.1700
Data Index: 2560483 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5656. Min Act: -0.1700
Data Index: 2186352 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5500. Min Act: -0.1700
Data Index: 911498 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6595. Min Range: -3.6595
Max Act: 3.5500. Min Act: -0.1700
Data Index: 5677035 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19