Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6666. Min Range: -10.6666
Max Act: 10.6666. Min Act: -0.1700
Data Index: 5287611 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6666. Min Range: -10.6666
Max Act: 10.2916. Min Act: -0.1700
Data Index: 166222 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6666. Min Range: -10.6666
Max Act: 10.2291. Min Act: -0.1700
Data Index: 2412458 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6666. Min Range: -10.6666
Max Act: 10.1666. Min Act: -0.1700
Data Index: 302563 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6666. Min Range: -10.6666
Max Act: 10.1041. Min Act: -0.1700
Data Index: 6034360 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6666. Min Range: -10.6666
Max Act: 10.1666. Min Act: -0.1700
Data Index: 2866209 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6666. Min Range: -10.6666
Max Act: 10.0416. Min Act: -0.1700
Data Index: 8528098 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.9166. Min Act: -0.1700
Data Index: 5526516 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.8541. Min Act: -0.1700
Data Index: 6926618 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.7916. Min Act: -0.1700
Data Index: 1847068 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.8541. Min Act: -0.1700
Data Index: 2412462 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.8541. Min Act: -0.1700
Data Index: 2106568 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.7916. Min Act: -0.1700
Data Index: 224872 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.7291. Min Act: -0.1700
Data Index: 383310 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.7291. Min Act: -0.1700
Data Index: 3743037 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.7291. Min Act: -0.1700
Data Index: 5341677 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.7291. Min Act: -0.1700
Data Index: 8048923 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.7291. Min Act: -0.1700
Data Index: 5862639 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.7291. Min Act: -0.1700
Data Index: 8235679 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6666. Min Range: -10.6666
Max Act: 9.6666. Min Act: -0.1700
Data Index: 5490825 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19