Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1666 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.2030. Min Act: -0.1700
Data Index: 6429357 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.2343. Min Act: -0.1700
Data Index: 312968 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.1093. Min Act: -0.1700
Data Index: 4298073 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.1093. Min Act: -0.1700
Data Index: 2826075 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.1093. Min Act: -0.1700
Data Index: 7733681 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.0780. Min Act: -0.1700
Data Index: 1938802 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.0468. Min Act: -0.1700
Data Index: 2974335 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.0780. Min Act: -0.1700
Data Index: 622738 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.0468. Min Act: -0.1700
Data Index: 8688850 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.0155. Min Act: -0.1700
Data Index: 3376983 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.0155. Min Act: -0.1700
Data Index: 6094032 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.0155. Min Act: -0.1700
Data Index: 1516877 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2343. Min Range: -4.2343
Max Act: 4.0155. Min Act: -0.1700
Data Index: 7763484 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2343. Min Range: -4.2343
Max Act: 3.9842. Min Act: -0.1700
Data Index: 3355651 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2343. Min Range: -4.2343
Max Act: 3.9842. Min Act: -0.1700
Data Index: 6831084 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2343. Min Range: -4.2343
Max Act: 3.9842. Min Act: -0.1700
Data Index: 8110044 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2343. Min Range: -4.2343
Max Act: 3.9842. Min Act: -0.1700
Data Index: 6500103 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2343. Min Range: -4.2343
Max Act: 3.9842. Min Act: -0.1700
Data Index: 5303027 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2343. Min Range: -4.2343
Max Act: 3.9842. Min Act: -0.1700
Data Index: 2050238 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2343. Min Range: -4.2343
Max Act: 3.9842. Min Act: -0.1700
Data Index: 5916496 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19