Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.9931. Min Act: -0.1700
Data Index: 4970684 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0556. Min Range: -5.0556
Max Act: 5.0556. Min Act: -0.1700
Data Index: 333034 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.9618. Min Act: -0.1700
Data Index: 3971321 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.9618. Min Act: -0.1700
Data Index: 2379952 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.9618. Min Act: -0.1700
Data Index: 2803354 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.8993. Min Act: -0.1700
Data Index: 6742643 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.9618. Min Act: -0.1700
Data Index: 3867583 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.8993. Min Act: -0.1700
Data Index: 2690217 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.8681. Min Act: -0.1700
Data Index: 30191 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.8368. Min Act: -0.1700
Data Index: 6363595 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.8368. Min Act: -0.1700
Data Index: 1880936 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.8368. Min Act: -0.1700
Data Index: 5220044 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.8368. Min Act: -0.1700
Data Index: 425143 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.7743. Min Act: -0.1700
Data Index: 4258511 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.7743. Min Act: -0.1700
Data Index: 5621320 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.8056. Min Act: -0.1700
Data Index: 4981188 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.7743. Min Act: -0.1700
Data Index: 1837246 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.7118. Min Act: -0.1700
Data Index: 7945332 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.7118. Min Act: -0.1700
Data Index: 356762 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0556. Min Range: -5.0556
Max Act: 4.7118. Min Act: -0.1700
Data Index: 3453316 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19