Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.8085. Min Act: -0.1700
Data Index: 6106188 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.6210. Min Act: -0.1700
Data Index: 997949 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.5585. Min Act: -0.1700
Data Index: 4799439 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.5585. Min Act: -0.1700
Data Index: 2618228 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.4335. Min Act: -0.1700
Data Index: 8218540 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.1835. Min Act: -0.1700
Data Index: 1407000 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.2460. Min Act: -0.1700
Data Index: 5432104 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.2460. Min Act: -0.1700
Data Index: 5424481 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.1835. Min Act: -0.1700
Data Index: 1712719 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.1835. Min Act: -0.1700
Data Index: 946629 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.1523. Min Act: -0.1700
Data Index: 3381812 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.0585. Min Act: -0.1700
Data Index: 926247 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.1210. Min Act: -0.1700
Data Index: 8780919 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8085. Min Range: -8.8085
Max Act: 8.0273. Min Act: -0.1700
Data Index: 5919933 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8085. Min Range: -8.8085
Max Act: 7.9023. Min Act: -0.1700
Data Index: 5883532 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8085. Min Range: -8.8085
Max Act: 7.7773. Min Act: -0.1700
Data Index: 7005494 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8085. Min Range: -8.8085
Max Act: 7.7148. Min Act: -0.1700
Data Index: 1946098 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8085. Min Range: -8.8085
Max Act: 7.7460. Min Act: -0.1700
Data Index: 2545416 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8085. Min Range: -8.8085
Max Act: 7.6523. Min Act: -0.1700
Data Index: 7024943 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8085. Min Range: -8.8085
Max Act: 7.6835. Min Act: -0.1700
Data Index: 8168001 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19