Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0760. Min Range: -4.0760
Max Act: 4.0760. Min Act: -0.1700
Data Index: 8626062 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0760. Min Range: -4.0760
Max Act: 4.0447. Min Act: -0.1700
Data Index: 2558548 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0760. Min Range: -4.0760
Max Act: 4.0135. Min Act: -0.1700
Data Index: 5109106 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0760. Min Range: -4.0760
Max Act: 4.0135. Min Act: -0.1700
Data Index: 8500240 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.9509. Min Act: -0.1700
Data Index: 1371302 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.9197. Min Act: -0.1700
Data Index: 201421 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.9197. Min Act: -0.1700
Data Index: 3194347 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.8884. Min Act: -0.1700
Data Index: 6486116 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.8884. Min Act: -0.1700
Data Index: 8398038 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.8571. Min Act: -0.1700
Data Index: 4502929 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.8571. Min Act: -0.1700
Data Index: 3803665 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.8259. Min Act: -0.1700
Data Index: 8143445 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.8259. Min Act: -0.1700
Data Index: 3684656 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.8259. Min Act: -0.1700
Data Index: 4145187 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.7946. Min Act: -0.1700
Data Index: 3355667 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.7946. Min Act: -0.1700
Data Index: 1808140 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.7633. Min Act: -0.1700
Data Index: 1089371 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.7633. Min Act: -0.1700
Data Index: 8471438 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.7633. Min Act: -0.1700
Data Index: 6017084 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0760. Min Range: -4.0760
Max Act: 3.7633. Min Act: -0.1700
Data Index: 5381027 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19