Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5118 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.5427. Min Act: -0.1700
Data Index: 3520983 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.5104. Min Act: -0.1700
Data Index: 8798178 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.4942. Min Act: -0.1700
Data Index: 7136059 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.4617. Min Act: -0.1700
Data Index: 717068 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.4129. Min Act: -0.1700
Data Index: 3359789 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.4129. Min Act: -0.1700
Data Index: 3106067 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3803. Min Act: -0.1700
Data Index: 558751 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3803. Min Act: -0.1700
Data Index: 7860255 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3639. Min Act: -0.1700
Data Index: 3347146 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3639. Min Act: -0.1700
Data Index: 2764531 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3639. Min Act: -0.1700
Data Index: 7824921 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3639. Min Act: -0.1700
Data Index: 3404543 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3639. Min Act: -0.1700
Data Index: 3215953 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3475. Min Act: -0.1700
Data Index: 2746452 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3475. Min Act: -0.1698
Data Index: 7459766 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3475. Min Act: -0.1700
Data Index: 3795913 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3311. Min Act: -0.1700
Data Index: 8610428 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3311. Min Act: -0.1699
Data Index: 5775472 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3147. Min Act: -0.1700
Data Index: 7694075 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5427. Min Range: -2.5427
Max Act: 2.3147. Min Act: -0.1700
Data Index: 5601481 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19