Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5951 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.3840. Min Act: -0.1700
Data Index: 4694733 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.2590. Min Act: -0.1700
Data Index: 5864186 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.1340. Min Act: -0.1700
Data Index: 8350731 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0403. Min Act: -0.1700
Data Index: 5750210 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0403. Min Act: -0.1700
Data Index: 2012019 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3840. Min Range: -7.3840
Max Act: 7.0403. Min Act: -0.1700
Data Index: 3716412 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.9465. Min Act: -0.1700
Data Index: 6067340 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8840. Min Act: -0.1700
Data Index: 3377554 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8840. Min Act: -0.1700
Data Index: 8298932 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8840. Min Act: -0.1700
Data Index: 1744961 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8528. Min Act: -0.1700
Data Index: 2276948 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8528. Min Act: -0.1700
Data Index: 7113061 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8840. Min Act: -0.1700
Data Index: 5670797 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8215. Min Act: -0.1700
Data Index: 2714057 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8215. Min Act: -0.1700
Data Index: 2710203 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8215. Min Act: -0.1700
Data Index: 4340507 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.8215. Min Act: -0.1700
Data Index: 4126469 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.7903. Min Act: -0.1700
Data Index: 5955217 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.7590. Min Act: -0.1700
Data Index: 183061 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3840. Min Range: -7.3840
Max Act: 6.7590. Min Act: -0.1700
Data Index: 4501461 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19