Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1891 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1301. Min Range: -8.1301
Max Act: 8.1301. Min Act: -0.1700
Data Index: 3059862 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1301. Min Range: -8.1301
Max Act: 8.0989. Min Act: -0.1697
Data Index: 6071782 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1301. Min Range: -8.1301
Max Act: 8.0676. Min Act: -0.1700
Data Index: 6786036 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.9114. Min Act: -0.1700
Data Index: 820622 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.8176. Min Act: -0.1700
Data Index: 7358224 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.7864. Min Act: -0.1700
Data Index: 6600318 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.7239. Min Act: -0.1700
Data Index: 6904191 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.6301. Min Act: -0.1700
Data Index: 4453062 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.6926. Min Act: -0.1700
Data Index: 1506493 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.5989. Min Act: -0.1700
Data Index: 6640304 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.5989. Min Act: -0.1700
Data Index: 4861750 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.5051. Min Act: -0.1700
Data Index: 2852398 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.5676. Min Act: -0.1700
Data Index: 4884082 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.5676. Min Act: -0.1700
Data Index: 2406317 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.4739. Min Act: -0.1700
Data Index: 6500284 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.4426. Min Act: -0.1700
Data Index: 8816138 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.3489. Min Act: -0.1700
Data Index: 1024142 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.2551. Min Act: -0.1700
Data Index: 5709385 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.0364. Min Act: -0.1700
Data Index: 7555037 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1301. Min Range: -8.1301
Max Act: 7.1301. Min Act: -0.1700
Data Index: 8680431 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19