Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.8580. Min Act: -0.1700
Data Index: 8613854 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.7017. Min Act: -0.1700
Data Index: 4534030 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.7017. Min Act: -0.1700
Data Index: 6161405 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.6705. Min Act: -0.1700
Data Index: 2618094 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.6705. Min Act: -0.1700
Data Index: 5816887 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.6705. Min Act: -0.1700
Data Index: 8161293 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5767. Min Act: -0.1700
Data Index: 6060980 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5767. Min Act: -0.1700
Data Index: 5894300 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5767. Min Act: -0.1700
Data Index: 7745025 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5455. Min Act: -0.1700
Data Index: 1634304 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5767. Min Act: -0.1700
Data Index: 6317936 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5142. Min Act: -0.1700
Data Index: 5664256 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5142. Min Act: -0.1700
Data Index: 364660 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5142. Min Act: -0.1700
Data Index: 3091371 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.4830. Min Act: -0.1700
Data Index: 6866536 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.4830. Min Act: -0.1700
Data Index: 889507 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.4830. Min Act: -0.1700
Data Index: 5387335 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.5142. Min Act: -0.1700
Data Index: 7236877 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.4830. Min Act: -0.1700
Data Index: 4538242 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8580. Min Range: -6.8580
Max Act: 6.4517. Min Act: -0.1700
Data Index: 7175792 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19