Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.6924. Min Act: -0.1700
Data Index: 8465288 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.6924. Min Act: -0.1700
Data Index: 7344546 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.6924. Min Act: -0.1700
Data Index: 5302118 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.6611. Min Act: -0.1700
Data Index: 844263 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.5986. Min Act: -0.1700
Data Index: 4573300 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.5361. Min Act: -0.1700
Data Index: 200557 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.5049. Min Act: -0.1700
Data Index: 8180394 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.4736. Min Act: -0.1700
Data Index: 5228886 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.4424. Min Act: -0.1700
Data Index: 3930367 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.4111. Min Act: -0.1700
Data Index: 3571068 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.4111. Min Act: -0.1700
Data Index: 4273906 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.3486. Min Act: -0.1700
Data Index: 858592 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.3174. Min Act: -0.1700
Data Index: 2379750 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.3486. Min Act: -0.1700
Data Index: 6727088 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.3174. Min Act: -0.1700
Data Index: 1701322 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.3174. Min Act: -0.1700
Data Index: 6501608 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.3174. Min Act: -0.1700
Data Index: 6275187 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.2549. Min Act: -0.1700
Data Index: 1225048 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.2861. Min Act: -0.1700
Data Index: 5123390 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6924. Min Range: -7.6924
Max Act: 7.2861. Min Act: -0.1700
Data Index: 4978455 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19