Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3665 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.7084. Min Act: -0.1700
Data Index: 5033145 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.4271. Min Act: -0.1700
Data Index: 6384814 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.3959. Min Act: -0.1700
Data Index: 1613936 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.3959. Min Act: -0.1700
Data Index: 7799675 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.3021. Min Act: -0.1700
Data Index: 1328111 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.2396. Min Act: -0.1700
Data Index: 3375191 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.2084. Min Act: -0.1700
Data Index: 8322705 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.1771. Min Act: -0.1700
Data Index: 2840125 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.1771. Min Act: -0.1700
Data Index: 3411752 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.1459. Min Act: -0.1700
Data Index: 2673989 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.0209. Min Act: -0.1700
Data Index: 4168625 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.0209. Min Act: -0.1700
Data Index: 6681629 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7084. Min Range: -5.7084
Max Act: 5.0209. Min Act: -0.1700
Data Index: 5305533 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7084. Min Range: -5.7084
Max Act: 4.9896. Min Act: -0.1700
Data Index: 4372981 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7084. Min Range: -5.7084
Max Act: 4.9896. Min Act: -0.1700
Data Index: 1946084 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7084. Min Range: -5.7084
Max Act: 4.9896. Min Act: -0.1700
Data Index: 5127265 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7084. Min Range: -5.7084
Max Act: 4.9271. Min Act: -0.1700
Data Index: 138449 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7084. Min Range: -5.7084
Max Act: 4.9271. Min Act: -0.1700
Data Index: 3467237 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7084. Min Range: -5.7084
Max Act: 4.9584. Min Act: -0.1700
Data Index: 2834265 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7084. Min Range: -5.7084
Max Act: 4.9584. Min Act: -0.1700
Data Index: 3185969 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19