Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1415 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.7761. Min Act: -0.1700
Data Index: 3922176 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.5573. Min Act: -0.1700
Data Index: 3256925 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.4948. Min Act: -0.1700
Data Index: 7370243 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.4948. Min Act: -0.1700
Data Index: 3323548 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.3073. Min Act: -0.1700
Data Index: 507667 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.3073. Min Act: -0.1700
Data Index: 7607202 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.2136. Min Act: -0.1700
Data Index: 6401853 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.1198. Min Act: -0.1700
Data Index: 7320064 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7761. Min Range: -7.7761
Max Act: 7.0573. Min Act: -0.1700
Data Index: 4011313 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.9636. Min Act: -0.1700
Data Index: 5342220 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.9323. Min Act: -0.1700
Data Index: 6315525 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.9323. Min Act: -0.1700
Data Index: 7659275 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.9323. Min Act: -0.1700
Data Index: 3741883 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.9011. Min Act: -0.1700
Data Index: 1347189 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.9323. Min Act: -0.1700
Data Index: 5148692 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.8698. Min Act: -0.1700
Data Index: 5775734 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.8386. Min Act: -0.1700
Data Index: 2578393 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.8386. Min Act: -0.1700
Data Index: 2422640 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.8386. Min Act: -0.1700
Data Index: 8367015 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7761. Min Range: -7.7761
Max Act: 6.8073. Min Act: -0.1700
Data Index: 1765648 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19