Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1877 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.8541. Min Act: -0.1700
Data Index: 759768 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.9166. Min Act: -0.1700
Data Index: 7430104 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.7916. Min Act: -0.1700
Data Index: 6620783 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.6666. Min Act: -0.1700
Data Index: 2636042 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.6666. Min Act: -0.1700
Data Index: 732995 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.6666. Min Act: -0.1700
Data Index: 654948 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.6041. Min Act: -0.1700
Data Index: 7177036 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.6041. Min Act: -0.1700
Data Index: 1346634 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.5416. Min Act: -0.1700
Data Index: 3279748 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.5416. Min Act: -0.1700
Data Index: 6951391 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.5416. Min Act: -0.1700
Data Index: 5734082 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.5416. Min Act: -0.1700
Data Index: 654942 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.5416. Min Act: -0.1700
Data Index: 4522665 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.5416. Min Act: -0.1700
Data Index: 4386820 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.4791. Min Act: -0.1700
Data Index: 8493521 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.4791. Min Act: -0.1700
Data Index: 5211743 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.4791. Min Act: -0.1700
Data Index: 3733960 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.4166. Min Act: -0.1700
Data Index: 2618354 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.4166. Min Act: -0.1700
Data Index: 5713896 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9166. Min Range: -10.9166
Max Act: 10.4166. Min Act: -0.1700
Data Index: 6527807 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19