Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 637 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0758. Min Act: -0.1700
Data Index: 3417653 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.1070. Min Act: -0.1700
Data Index: 5200512 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0758. Min Act: -0.1700
Data Index: 2419511 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0445. Min Act: -0.1700
Data Index: 1006312 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9820. Min Act: -0.1700
Data Index: 7004910 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9195. Min Act: -0.1700
Data Index: 2391502 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9195. Min Act: -0.1700
Data Index: 6768532 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9195. Min Act: -0.1700
Data Index: 5715985 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8883. Min Act: -0.1700
Data Index: 6582890 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9195. Min Act: -0.1700
Data Index: 4427602 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8883. Min Act: -0.1700
Data Index: 7545992 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8570. Min Act: -0.1700
Data Index: 1277684 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8570. Min Act: -0.1700
Data Index: 3100219 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8883. Min Act: -0.1700
Data Index: 2582521 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8258. Min Act: -0.1700
Data Index: 850766 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7945. Min Act: -0.1700
Data Index: 1028843 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7945. Min Act: -0.1700
Data Index: 7531570 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7633. Min Act: -0.1700
Data Index: 1028854 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7633. Min Act: -0.1700
Data Index: 6560226 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7945. Min Act: -0.1700
Data Index: 5849001 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19