Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6305 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.6134. Min Act: -0.1700
Data Index: 1498893 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.5509. Min Act: -0.1700
Data Index: 6150453 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.5196. Min Act: -0.1700
Data Index: 3055428 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.4884. Min Act: -0.1700
Data Index: 2389113 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.4884. Min Act: -0.1700
Data Index: 1082671 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.4259. Min Act: -0.1700
Data Index: 2545882 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.4571. Min Act: -0.1700
Data Index: 7423692 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.4259. Min Act: -0.1700
Data Index: 1810414 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.4259. Min Act: -0.1700
Data Index: 2308640 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3946. Min Act: -0.1700
Data Index: 2063529 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.4259. Min Act: -0.1700
Data Index: 1436095 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.4259. Min Act: -0.1700
Data Index: 1991977 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3946. Min Act: -0.1700
Data Index: 8259893 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3946. Min Act: -0.1700
Data Index: 3130990 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3946. Min Act: -0.1700
Data Index: 5402651 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3634. Min Act: -0.1700
Data Index: 1059148 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3634. Min Act: -0.1700
Data Index: 4201311 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3634. Min Act: -0.1700
Data Index: 7378969 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3634. Min Act: -0.1700
Data Index: 4308629 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6134. Min Range: -5.6134
Max Act: 5.3634. Min Act: -0.1700
Data Index: 4427392 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19