Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1918 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.7532. Min Act: -0.1700
Data Index: 6027710 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.6595. Min Act: -0.1700
Data Index: 7624772 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.4407. Min Act: -0.1700
Data Index: 1579374 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.4407. Min Act: -0.1700
Data Index: 7322121 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.4407. Min Act: -0.1700
Data Index: 6813263 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.4407. Min Act: -0.1700
Data Index: 8533469 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3470. Min Act: -0.1700
Data Index: 4024934 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3782. Min Act: -0.1700
Data Index: 4030164 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.4095. Min Act: -0.1700
Data Index: 5543598 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3470. Min Act: -0.1700
Data Index: 5680353 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3470. Min Act: -0.1700
Data Index: 4933104 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3470. Min Act: -0.1700
Data Index: 5680357 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3157. Min Act: -0.1700
Data Index: 8829975 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3157. Min Act: -0.1700
Data Index: 2817060 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3157. Min Act: -0.1700
Data Index: 4859371 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.2532. Min Act: -0.1700
Data Index: 5691248 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.2845. Min Act: -0.1700
Data Index: 4860569 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.3157. Min Act: -0.1700
Data Index: 457824 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.2219. Min Act: -0.1700
Data Index: 2744932 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7532. Min Range: -4.7532
Max Act: 4.2845. Min Act: -0.1700
Data Index: 5610480 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19