Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.2179. Min Act: -0.1700
Data Index: 4317356 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5519255 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.2492. Min Act: -0.1700
Data Index: 126269 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1867. Min Act: -0.1700
Data Index: 1835606 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1554. Min Act: -0.1700
Data Index: 4390645 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1554. Min Act: -0.1700
Data Index: 2108767 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1242. Min Act: -0.1700
Data Index: 1518653 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0929. Min Act: -0.1700
Data Index: 3044117 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1242. Min Act: -0.1700
Data Index: 2300736 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0929. Min Act: -0.1699
Data Index: 5525707 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0304. Min Act: -0.1700
Data Index: 3088814 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0929. Min Act: -0.1700
Data Index: 6673296 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0617. Min Act: -0.1700
Data Index: 7928486 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0617. Min Act: -0.1700
Data Index: 7159977 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0617. Min Act: -0.1700
Data Index: 5726930 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9992. Min Act: -0.1700
Data Index: 4656236 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0617. Min Act: -0.1700
Data Index: 3739884 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0304. Min Act: -0.1700
Data Index: 6810086 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0304. Min Act: -0.1700
Data Index: 7365218 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9992. Min Act: -0.1700
Data Index: 4851119 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19