Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.9683. Min Act: -0.1700
Data Index: 7561947 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8432. Min Act: -0.1700
Data Index: 3024876 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8432. Min Act: -0.1700
Data Index: 4652618 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8432. Min Act: -0.1700
Data Index: 8656727 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8432. Min Act: -0.1700
Data Index: 737798 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8120. Min Act: -0.1700
Data Index: 3145274 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8120. Min Act: -0.1700
Data Index: 2843513 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8120. Min Act: -0.1700
Data Index: 6736875 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8120. Min Act: -0.1700
Data Index: 3680644 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7807. Min Act: -0.1700
Data Index: 6105181 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7807. Min Act: -0.1700
Data Index: 6008740 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7807. Min Act: -0.1700
Data Index: 6576100 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.8120. Min Act: -0.1700
Data Index: 3497341 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7494. Min Act: -0.1700
Data Index: 210415 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7494. Min Act: -0.1700
Data Index: 6537344 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7494. Min Act: -0.1700
Data Index: 1580632 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7494. Min Act: -0.1700
Data Index: 1811514 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7338. Min Act: -0.1700
Data Index: 707563 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7338. Min Act: -0.1700
Data Index: 3258264 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9683. Min Range: -3.9683
Max Act: 3.7181. Min Act: -0.1700
Data Index: 2191502 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19