Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4579 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4103. Min Range: -7.4103
Max Act: 7.4103. Min Act: -0.1700
Data Index: 1374412 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4103. Min Range: -7.4103
Max Act: 7.3166. Min Act: -0.1700
Data Index: 315407 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4103. Min Range: -7.4103
Max Act: 7.3478. Min Act: -0.1700
Data Index: 7649755 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4103. Min Range: -7.4103
Max Act: 7.2541. Min Act: -0.1700
Data Index: 3382727 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4103. Min Range: -7.4103
Max Act: 7.0353. Min Act: -0.1700
Data Index: 7618807 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4103. Min Range: -7.4103
Max Act: 7.0041. Min Act: -0.1700
Data Index: 1687059 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.9416. Min Act: -0.1700
Data Index: 1577601 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.9416. Min Act: -0.1700
Data Index: 7250017 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.9103. Min Act: -0.1700
Data Index: 6737373 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.9103. Min Act: -0.1700
Data Index: 7720204 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.8791. Min Act: -0.1700
Data Index: 8759922 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.8791. Min Act: -0.1700
Data Index: 3554731 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.9103. Min Act: -0.1700
Data Index: 3394368 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.8791. Min Act: -0.1700
Data Index: 3328321 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.8478. Min Act: -0.1700
Data Index: 8422452 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.8478. Min Act: -0.1700
Data Index: 7053544 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.8166. Min Act: -0.1700
Data Index: 2594113 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.8166. Min Act: -0.1700
Data Index: 2892280 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.8166. Min Act: -0.1700
Data Index: 4606770 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4103. Min Range: -7.4103
Max Act: 6.7853. Min Act: -0.1700
Data Index: 4323429 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19