Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.6580. Min Act: -0.1700
Data Index: 7557167 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.6267. Min Act: -0.1700
Data Index: 2748491 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.6267. Min Act: -0.1700
Data Index: 2977273 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.5330. Min Act: -0.1700
Data Index: 8577378 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.4392. Min Act: -0.1700
Data Index: 4867164 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.3455. Min Act: -0.1700
Data Index: 5855251 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2830. Min Act: -0.1700
Data Index: 4859363 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.3767. Min Act: -0.1700
Data Index: 295726 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.3455. Min Act: -0.1700
Data Index: 5175453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.3455. Min Act: -0.1700
Data Index: 4722236 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.3767. Min Act: -0.1700
Data Index: 1128925 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2830. Min Act: -0.1700
Data Index: 2612463 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2830. Min Act: -0.1700
Data Index: 1057551 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2830. Min Act: -0.1700
Data Index: 1019864 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2830. Min Act: -0.1700
Data Index: 1801004 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2517. Min Act: -0.1700
Data Index: 1097110 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2830. Min Act: -0.1700
Data Index: 858929 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2830. Min Act: -0.1700
Data Index: 7764397 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2830. Min Act: -0.1700
Data Index: 2556984 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6580. Min Range: -4.6580
Max Act: 4.2517. Min Act: -0.1700
Data Index: 4957692 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19