Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1265 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0901. Min Range: -7.0901
Max Act: 7.0901. Min Act: -0.1700
Data Index: 481186 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.8714. Min Act: -0.1700
Data Index: 2828018 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.8089. Min Act: -0.1700
Data Index: 4583770 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.8401. Min Act: -0.1700
Data Index: 1989876 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.8089. Min Act: -0.1700
Data Index: 3359263 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.8401. Min Act: -0.1700
Data Index: 2944835 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.8089. Min Act: -0.1700
Data Index: 4075446 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.7776. Min Act: -0.1700
Data Index: 1777361 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.7776. Min Act: -0.1700
Data Index: 3458614 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.7464. Min Act: -0.1700
Data Index: 1070468 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.7464. Min Act: -0.1700
Data Index: 6655980 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.7151. Min Act: -0.1700
Data Index: 3656045 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.7464. Min Act: -0.1700
Data Index: 6738652 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.7151. Min Act: -0.1700
Data Index: 1138637 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.6526. Min Act: -0.1700
Data Index: 5880714 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.6526. Min Act: -0.1700
Data Index: 5337449 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.6839. Min Act: -0.1700
Data Index: 122225 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.6839. Min Act: -0.1700
Data Index: 8625588 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.6839. Min Act: -0.1700
Data Index: 449694 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0901. Min Range: -7.0901
Max Act: 6.6526. Min Act: -0.1700
Data Index: 1335625 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19