Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0483. Min Range: -7.0483
Max Act: 7.0483. Min Act: -0.1700
Data Index: 1181166 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.8295. Min Act: -0.1700
Data Index: 4733016 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.7670. Min Act: -0.1700
Data Index: 6052837 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.7045. Min Act: -0.1700
Data Index: 671136 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.7358. Min Act: -0.1700
Data Index: 7765547 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.6420. Min Act: -0.1700
Data Index: 4304187 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.6420. Min Act: -0.1700
Data Index: 7009266 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.5795. Min Act: -0.1700
Data Index: 7562355 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.5795. Min Act: -0.1700
Data Index: 3373907 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.5795. Min Act: -0.1700
Data Index: 1892489 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.5483. Min Act: -0.1700
Data Index: 6057608 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.5170. Min Act: -0.1700
Data Index: 7019442 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.5170. Min Act: -0.1700
Data Index: 1967171 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.4545. Min Act: -0.1700
Data Index: 8228560 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.4858. Min Act: -0.1700
Data Index: 7462419 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.4545. Min Act: -0.1700
Data Index: 2920623 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.4545. Min Act: -0.1700
Data Index: 3123126 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.4233. Min Act: -0.1700
Data Index: 7885698 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.4233. Min Act: -0.1700
Data Index: 5033359 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0483. Min Range: -7.0483
Max Act: 6.4233. Min Act: -0.1700
Data Index: 4585849 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19