Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1683. Min Range: -6.1683
Max Act: 6.1683. Min Act: -0.1700
Data Index: 4709173 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1683. Min Range: -6.1683
Max Act: 6.0433. Min Act: -0.1700
Data Index: 8688192 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.9808. Min Act: -0.1700
Data Index: 7141700 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.9495. Min Act: -0.1700
Data Index: 8424779 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.9495. Min Act: -0.1700
Data Index: 6947064 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.9495. Min Act: -0.1700
Data Index: 721993 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.9183. Min Act: -0.1700
Data Index: 8218236 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.8245. Min Act: -0.1700
Data Index: 5611932 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.7933. Min Act: -0.1700
Data Index: 7746528 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.7620. Min Act: -0.1700
Data Index: 6196153 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.7620. Min Act: -0.1700
Data Index: 106992 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.7620. Min Act: -0.1700
Data Index: 6770004 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.7308. Min Act: -0.1700
Data Index: 4255653 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.6995. Min Act: -0.1700
Data Index: 6321053 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.7308. Min Act: -0.1700
Data Index: 3907138 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.7308. Min Act: -0.1700
Data Index: 2215593 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.6995. Min Act: -0.1700
Data Index: 7537204 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.6995. Min Act: -0.1700
Data Index: 744607 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.6683. Min Act: -0.1700
Data Index: 3730830 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1683. Min Range: -6.1683
Max Act: 5.6995. Min Act: -0.1700
Data Index: 2333278 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19