Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3879 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2065. Min Range: -12.2065
Max Act: 12.2065. Min Act: -0.1700
Data Index: 4268858 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.7690. Min Act: -0.1700
Data Index: 5489715 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.6440. Min Act: -0.1700
Data Index: 6803307 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.5815. Min Act: -0.1700
Data Index: 6518564 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.5815. Min Act: -0.1700
Data Index: 5227453 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.5190. Min Act: -0.1700
Data Index: 3268458 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.5190. Min Act: -0.1700
Data Index: 8098610 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.3315. Min Act: -0.1700
Data Index: 1582486 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.2065. Min Act: -0.1700
Data Index: 5200027 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.2065. Min Act: -0.1700
Data Index: 5043727 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.0815. Min Act: -0.1700
Data Index: 1339475 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.0815. Min Act: -0.1700
Data Index: 4016035 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2065. Min Range: -12.2065
Max Act: 11.0190. Min Act: -0.1700
Data Index: 6603898 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2065. Min Range: -12.2065
Max Act: 10.9565. Min Act: -0.1700
Data Index: 8120611 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2065. Min Range: -12.2065
Max Act: 10.8940. Min Act: -0.1700
Data Index: 8614440 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2065. Min Range: -12.2065
Max Act: 10.8940. Min Act: -0.1700
Data Index: 5248102 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2065. Min Range: -12.2065
Max Act: 10.8940. Min Act: -0.1700
Data Index: 8120606 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2065. Min Range: -12.2065
Max Act: 10.7690. Min Act: -0.1700
Data Index: 771985 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2065. Min Range: -12.2065
Max Act: 10.8315. Min Act: -0.1700
Data Index: 5374401 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2065. Min Range: -12.2065
Max Act: 10.8315. Min Act: -0.1700
Data Index: 2620626 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19