Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0437. Min Act: -0.1700
Data Index: 1985546 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0437. Min Act: -0.1700
Data Index: 2868841 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0437. Min Act: -0.1700
Data Index: 5702267 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0749. Min Act: -0.1700
Data Index: 4553886 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0437. Min Act: -0.1700
Data Index: 2698855 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0437. Min Act: -0.1700
Data Index: 4637888 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0437. Min Act: -0.1700
Data Index: 2836676 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0749. Min Range: -5.0749
Max Act: 5.0124. Min Act: -0.1700
Data Index: 6386135 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9812. Min Act: -0.1700
Data Index: 4199630 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9812. Min Act: -0.1700
Data Index: 7143481 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9812. Min Act: -0.1700
Data Index: 3921692 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9812. Min Act: -0.1700
Data Index: 5075527 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9812. Min Act: -0.1700
Data Index: 4926439 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9499. Min Act: -0.1700
Data Index: 6745002 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9187. Min Act: -0.1700
Data Index: 1992671 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9499. Min Act: -0.1700
Data Index: 8167061 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9812. Min Act: -0.1700
Data Index: 175143 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9187. Min Act: -0.1700
Data Index: 4658398 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9187. Min Act: -0.1700
Data Index: 8569778 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0749. Min Range: -5.0749
Max Act: 4.9499. Min Act: -0.1700
Data Index: 4863111 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19