Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.5331. Min Act: -0.1700
Data Index: 271468 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.5957. Min Act: -0.1700
Data Index: 4536868 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.5018. Min Act: -0.1700
Data Index: 1295726 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.5018. Min Act: -0.1700
Data Index: 5422343 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.4391. Min Act: -0.1700
Data Index: 130671 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.3764. Min Act: -0.1700
Data Index: 7241715 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.4078. Min Act: -0.1700
Data Index: 6297232 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.4078. Min Act: -0.1700
Data Index: 7917927 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.3921. Min Act: -0.1700
Data Index: 1805375 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.3764. Min Act: -0.1700
Data Index: 2789825 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.3451. Min Act: -0.1700
Data Index: 4006236 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2980. Min Act: -0.1700
Data Index: 1363035 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2666. Min Act: -0.1700
Data Index: 2830878 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2980. Min Act: -0.1700
Data Index: 3357543 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2666. Min Act: -0.1700
Data Index: 5176000 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2823. Min Act: -0.1700
Data Index: 2629699 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2351. Min Act: -0.1700
Data Index: 7636629 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2666. Min Act: -0.1700
Data Index: 5509907 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2509. Min Act: -0.1700
Data Index: 5659821 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5957. Min Range: -3.5957
Max Act: 3.2351. Min Act: -0.1700
Data Index: 2987965 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19