Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.5334. Min Act: -0.1700
Data Index: 4782945 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.5334. Min Act: -0.1700
Data Index: 2352366 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.4397. Min Act: -0.1700
Data Index: 4337392 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.4084. Min Act: -0.1700
Data Index: 1338554 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.4397. Min Act: -0.1700
Data Index: 6983694 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.4084. Min Act: -0.1700
Data Index: 3088137 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.3772. Min Act: -0.1700
Data Index: 5036412 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.3772. Min Act: -0.1700
Data Index: 8462739 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.3459. Min Act: -0.1700
Data Index: 200441 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.3147. Min Act: -0.1700
Data Index: 268871 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.3459. Min Act: -0.1700
Data Index: 4967895 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.3459. Min Act: -0.1700
Data Index: 692164 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.2834. Min Act: -0.1700
Data Index: 5268400 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.3147. Min Act: -0.1700
Data Index: 3960435 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.3147. Min Act: -0.1700
Data Index: 428032 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.2834. Min Act: -0.1700
Data Index: 7317422 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.2834. Min Act: -0.1700
Data Index: 1418520 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.2834. Min Act: -0.1700
Data Index: 4970679 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.2834. Min Act: -0.1700
Data Index: 7016185 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5334. Min Range: -5.5334
Max Act: 5.2834. Min Act: -0.1700
Data Index: 3572527 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19