Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6356 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.6494. Min Act: -0.1700
Data Index: 2815619 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.6494. Min Act: -0.1700
Data Index: 6015199 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.6494. Min Act: -0.1700
Data Index: 8134662 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.6182. Min Act: -0.1700
Data Index: 137864 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.6182. Min Act: -0.1700
Data Index: 2384326 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5869. Min Act: -0.1700
Data Index: 2387892 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5557. Min Act: -0.1700
Data Index: 3269062 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5869. Min Act: -0.1700
Data Index: 6597300 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 2062740 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 8372765 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.5244. Min Act: -0.1700
Data Index: 1195114 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 263056 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 569108 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 1088608 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4619. Min Act: -0.1700
Data Index: 434450 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4307. Min Act: -0.1700
Data Index: 4301028 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4307. Min Act: -0.1700
Data Index: 1916651 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4307. Min Act: -0.1700
Data Index: 5074218 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4307. Min Act: -0.1700
Data Index: 2757757 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6494. Min Range: -5.6494
Max Act: 5.4307. Min Act: -0.1700
Data Index: 5074224 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19