Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1136 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1076. Min Range: -4.1076
Max Act: 4.1076. Min Act: -0.1700
Data Index: 2852520 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1076. Min Range: -4.1076
Max Act: 4.0764. Min Act: -0.1700
Data Index: 5842698 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1076. Min Range: -4.1076
Max Act: 4.0451. Min Act: -0.1700
Data Index: 2806275 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.9513. Min Act: -0.1700
Data Index: 5085619 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.9826. Min Act: -0.1700
Data Index: 2897345 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.9513. Min Act: -0.1700
Data Index: 4164480 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.9513. Min Act: -0.1700
Data Index: 234415 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.9201. Min Act: -0.1700
Data Index: 6778099 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8888. Min Act: -0.1700
Data Index: 5825389 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.9201. Min Act: -0.1700
Data Index: 495231 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.9201. Min Act: -0.1700
Data Index: 4496268 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.9201. Min Act: -0.1700
Data Index: 6645656 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8575. Min Act: -0.1700
Data Index: 3541171 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8888. Min Act: -0.1700
Data Index: 3120677 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8888. Min Act: -0.1700
Data Index: 2149478 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8888. Min Act: -0.1700
Data Index: 5647750 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8888. Min Act: -0.1700
Data Index: 767179 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8888. Min Act: -0.1700
Data Index: 22585 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8575. Min Act: -0.1700
Data Index: 344926 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1076. Min Range: -4.1076
Max Act: 3.8575. Min Act: -0.1700
Data Index: 5155015 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19