Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.8560. Min Act: -0.1700
Data Index: 6753512 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.8560. Min Act: -0.1700
Data Index: 3687507 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.8247. Min Act: -0.1700
Data Index: 3769082 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.8247. Min Act: -0.1700
Data Index: 844538 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.7935. Min Act: -0.1700
Data Index: 5673476 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.7935. Min Act: -0.1700
Data Index: 4196162 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.7622. Min Act: -0.1700
Data Index: 546791 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.7622. Min Act: -0.1700
Data Index: 4088698 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.7310. Min Act: -0.1700
Data Index: 7477701 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.7622. Min Act: -0.1700
Data Index: 3044957 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.7310. Min Act: -0.1700
Data Index: 2217010 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6997. Min Act: -0.1700
Data Index: 3206450 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6997. Min Act: -0.1700
Data Index: 2570305 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6997. Min Act: -0.1700
Data Index: 7257931 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6685. Min Act: -0.1700
Data Index: 4127351 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6685. Min Act: -0.1700
Data Index: 7249466 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6685. Min Act: -0.1700
Data Index: 5470328 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6060. Min Act: -0.1700
Data Index: 3693787 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6372. Min Act: -0.1700
Data Index: 386465 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8560. Min Range: -4.8560
Max Act: 4.6060. Min Act: -0.1700
Data Index: 86349 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19