Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4336 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.4023. Min Act: -0.1700
Data Index: 4208313 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.1523. Min Act: -0.1700
Data Index: 5027350 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.1523. Min Act: -0.1700
Data Index: 5031696 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.0898. Min Act: -0.1700
Data Index: 6011226 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.0585. Min Act: -0.1700
Data Index: 4225771 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.0273. Min Act: -0.1700
Data Index: 565170 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9960. Min Act: -0.1700
Data Index: 2461551 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9960. Min Act: -0.1700
Data Index: 4123291 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9648. Min Act: -0.1700
Data Index: 3163390 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9648. Min Act: -0.1700
Data Index: 4225769 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9023. Min Act: -0.1700
Data Index: 5105075 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.7773. Min Act: -0.1700
Data Index: 8380809 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.7460. Min Act: -0.1700
Data Index: 8029661 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.7460. Min Act: -0.1700
Data Index: 8785105 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 7891559 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 319805 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 7067848 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.7460. Min Act: -0.1700
Data Index: 5792451 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 7946494 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.6523. Min Act: -0.1700
Data Index: 3587354 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19