Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2135 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1586. Min Range: -5.1586
Max Act: 5.1586. Min Act: -0.1700
Data Index: 4397079 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1586. Min Range: -5.1586
Max Act: 5.1586. Min Act: -0.1700
Data Index: 1333432 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1586. Min Range: -5.1586
Max Act: 5.0961. Min Act: -0.1700
Data Index: 8384987 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1586. Min Range: -5.1586
Max Act: 5.0649. Min Act: -0.1700
Data Index: 1047546 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1586. Min Range: -5.1586
Max Act: 5.0024. Min Act: -0.1700
Data Index: 18462 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1586. Min Range: -5.1586
Max Act: 5.0024. Min Act: -0.1700
Data Index: 1513459 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.9399. Min Act: -0.1700
Data Index: 908187 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.9086. Min Act: -0.1700
Data Index: 3242988 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.9399. Min Act: -0.1700
Data Index: 274316 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.9399. Min Act: -0.1700
Data Index: 8113622 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.9086. Min Act: -0.1700
Data Index: 3636367 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.9086. Min Act: -0.1700
Data Index: 8301666 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.8774. Min Act: -0.1700
Data Index: 4121834 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.8774. Min Act: -0.1700
Data Index: 7433905 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.8461. Min Act: -0.1700
Data Index: 1318452 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.8149. Min Act: -0.1700
Data Index: 4631362 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.7836. Min Act: -0.1700
Data Index: 1778554 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.8149. Min Act: -0.1700
Data Index: 6018641 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.8149. Min Act: -0.1700
Data Index: 1318453 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1586. Min Range: -5.1586
Max Act: 4.7836. Min Act: -0.1700
Data Index: 209015 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19