Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0476. Min Range: -5.0476
Max Act: 5.0476. Min Act: -0.1700
Data Index: 449117 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0476. Min Range: -5.0476
Max Act: 5.0476. Min Act: -0.1700
Data Index: 5440424 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.9226. Min Act: -0.1700
Data Index: 1748328 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.8913. Min Act: -0.1700
Data Index: 7748701 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.8288. Min Act: -0.1700
Data Index: 5742418 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7351. Min Act: -0.1700
Data Index: 687028 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7663. Min Act: -0.1700
Data Index: 5212946 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7663. Min Act: -0.1700
Data Index: 7775477 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7663. Min Act: -0.1700
Data Index: 7196067 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7663. Min Act: -0.1700
Data Index: 1826256 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7351. Min Act: -0.1700
Data Index: 4347286 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7351. Min Act: -0.1700
Data Index: 6008127 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7351. Min Act: -0.1700
Data Index: 6879271 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7038. Min Act: -0.1700
Data Index: 3770660 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7038. Min Act: -0.1700
Data Index: 3770673 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7038. Min Act: -0.1700
Data Index: 1106493 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.6726. Min Act: -0.1700
Data Index: 1784768 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7038. Min Act: -0.1700
Data Index: 3843186 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.7038. Min Act: -0.1700
Data Index: 98749 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0476. Min Range: -5.0476
Max Act: 4.6726. Min Act: -0.1700
Data Index: 3937837 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19