Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 805 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2071. Min Range: -4.2071
Max Act: 4.2071. Min Act: -0.1700
Data Index: 3851937 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2071. Min Range: -4.2071
Max Act: 4.2071. Min Act: -0.1700
Data Index: 592109 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2071. Min Range: -4.2071
Max Act: 4.1134. Min Act: -0.1700
Data Index: 4076377 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2071. Min Range: -4.2071
Max Act: 4.0508. Min Act: -0.1700
Data Index: 3322156 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2071. Min Range: -4.2071
Max Act: 4.0821. Min Act: -0.1700
Data Index: 3299616 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2071. Min Range: -4.2071
Max Act: 4.0196. Min Act: -0.1700
Data Index: 3299614 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2071. Min Range: -4.2071
Max Act: 4.0508. Min Act: -0.1700
Data Index: 6385161 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2071. Min Range: -4.2071
Max Act: 4.0196. Min Act: -0.1700
Data Index: 6280309 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.9883. Min Act: -0.1700
Data Index: 2496710 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.9571. Min Act: -0.1700
Data Index: 6646627 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.9571. Min Act: -0.1700
Data Index: 6018139 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.9571. Min Act: -0.1700
Data Index: 3299618 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.9571. Min Act: -0.1700
Data Index: 6758603 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.8945. Min Act: -0.1700
Data Index: 102589 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.9258. Min Act: -0.1700
Data Index: 3299615 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.9258. Min Act: -0.1700
Data Index: 773651 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.8633. Min Act: -0.1700
Data Index: 215244 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.8945. Min Act: -0.1700
Data Index: 6037241 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.8633. Min Act: -0.1700
Data Index: 5029201 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2071. Min Range: -4.2071
Max Act: 3.8945. Min Act: -0.1700
Data Index: 996170 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19