Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0358. Min Range: -5.0358
Max Act: 5.0358. Min Act: -0.1700
Data Index: 766399 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.9421. Min Act: -0.1700
Data Index: 141655 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.9108. Min Act: -0.1700
Data Index: 5062783 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.7858. Min Act: -0.1700
Data Index: 1064148 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.7858. Min Act: -0.1700
Data Index: 1678424 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.7546. Min Act: -0.1700
Data Index: 6544182 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.7546. Min Act: -0.1700
Data Index: 4004716 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.7233. Min Act: -0.1700
Data Index: 3049782 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6921. Min Act: -0.1700
Data Index: 8311211 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6608. Min Act: -0.1700
Data Index: 5335928 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6608. Min Act: -0.1700
Data Index: 5359260 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6608. Min Act: -0.1700
Data Index: 4778145 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6608. Min Act: -0.1700
Data Index: 7339532 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6921. Min Act: -0.1700
Data Index: 6391530 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6608. Min Act: -0.1700
Data Index: 8617137 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6296. Min Act: -0.1700
Data Index: 8742064 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6296. Min Act: -0.1700
Data Index: 3480856 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.6608. Min Act: -0.1700
Data Index: 1407301 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.5983. Min Act: -0.1700
Data Index: 3605633 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0358. Min Range: -5.0358
Max Act: 4.5983. Min Act: -0.1700
Data Index: 390225 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19