Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4020 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.7424. Min Act: -0.1700
Data Index: 1817867 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.7111. Min Act: -0.1700
Data Index: 3851285 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.5549. Min Act: -0.1700
Data Index: 816488 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.5549. Min Act: -0.1700
Data Index: 3851291 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.5236. Min Act: -0.1700
Data Index: 1800843 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.5236. Min Act: -0.1700
Data Index: 3341786 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.4611. Min Act: -0.1700
Data Index: 2575786 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.3674. Min Act: -0.1700
Data Index: 3195610 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.3361. Min Act: -0.1700
Data Index: 7886453 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.3361. Min Act: -0.1700
Data Index: 2575781 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.3361. Min Act: -0.1700
Data Index: 7622368 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.2736. Min Act: -0.1700
Data Index: 4111996 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.2736. Min Act: -0.1700
Data Index: 2575792 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.3049. Min Act: -0.1700
Data Index: 2575797 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.3049. Min Act: -0.1700
Data Index: 7886459 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.2736. Min Act: -0.1700
Data Index: 3030298 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.2424. Min Act: -0.1700
Data Index: 8068939 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.2424. Min Act: -0.1700
Data Index: 1800844 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.2111. Min Act: -0.1700
Data Index: 7886449 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7424. Min Range: -5.7424
Max Act: 5.2424. Min Act: -0.1700
Data Index: 1800846 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19