Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.6676. Min Act: -0.1700
Data Index: 5482142 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.5738. Min Act: -0.1700
Data Index: 3895459 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.5426. Min Act: -0.1700
Data Index: 8330877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.5426. Min Act: -0.1700
Data Index: 381119 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.5113. Min Act: -0.1679
Data Index: 3648553 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.5113. Min Act: -0.1700
Data Index: 3278521 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.4801. Min Act: -0.1700
Data Index: 5352402 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.4801. Min Act: -0.1700
Data Index: 3895481 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.4488. Min Act: -0.1700
Data Index: 8034855 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.4175. Min Act: -0.1700
Data Index: 7824200 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.4488. Min Act: -0.1700
Data Index: 686485 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.4488. Min Act: -0.1700
Data Index: 5309045 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.4175. Min Act: -0.1700
Data Index: 7502124 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.4175. Min Act: -0.1700
Data Index: 2694912 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.3863. Min Act: -0.1700
Data Index: 6076928 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.3863. Min Act: -0.1700
Data Index: 1742560 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.3863. Min Act: -0.1700
Data Index: 4128647 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.3863. Min Act: -0.1700
Data Index: 3895482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.3863. Min Act: -0.1700
Data Index: 2551185 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6676. Min Range: -4.6676
Max Act: 4.3863. Min Act: -0.1700
Data Index: 6076925 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19