Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1579. Min Range: -4.1579
Max Act: 4.1579. Min Act: -0.1700
Data Index: 2738192 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1579. Min Range: -4.1579
Max Act: 4.0641. Min Act: -0.1700
Data Index: 1647394 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.8765. Min Act: -0.1700
Data Index: 1757050 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.8453. Min Act: -0.1700
Data Index: 5409378 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.8140. Min Act: -0.1700
Data Index: 8746697 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.8140. Min Act: -0.1700
Data Index: 2918261 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7827. Min Act: -0.1700
Data Index: 4353583 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7671. Min Act: -0.1700
Data Index: 6945477 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7671. Min Act: -0.1700
Data Index: 4992817 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7358. Min Act: -0.1700
Data Index: 5139901 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7202. Min Act: -0.1700
Data Index: 7027606 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7358. Min Act: -0.1700
Data Index: 3532328 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7202. Min Act: -0.1700
Data Index: 102864 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7045. Min Act: -0.1700
Data Index: 7171430 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.7045. Min Act: -0.1700
Data Index: 331259 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.6889. Min Act: -0.1700
Data Index: 1720685 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.6732. Min Act: -0.1700
Data Index: 3915859 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.6576. Min Act: -0.1700
Data Index: 3150486 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.6576. Min Act: -0.1700
Data Index: 7028116 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1579. Min Range: -4.1579
Max Act: 3.6576. Min Act: -0.1700
Data Index: 2615527 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19