Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3858. Min Range: -6.3858
Max Act: 6.3858. Min Act: -0.1700
Data Index: 3016799 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3858. Min Range: -6.3858
Max Act: 6.2608. Min Act: -0.1700
Data Index: 637209 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3858. Min Range: -6.3858
Max Act: 6.1670. Min Act: -0.1700
Data Index: 6876397 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3858. Min Range: -6.3858
Max Act: 6.0733. Min Act: -0.1700
Data Index: 6218910 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3858. Min Range: -6.3858
Max Act: 6.0420. Min Act: -0.1700
Data Index: 369457 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3858. Min Range: -6.3858
Max Act: 6.0420. Min Act: -0.1700
Data Index: 5666766 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3858. Min Range: -6.3858
Max Act: 6.0108. Min Act: -0.1700
Data Index: 5451339 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3858. Min Range: -6.3858
Max Act: 6.0108. Min Act: -0.1700
Data Index: 6623586 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.9795. Min Act: -0.1700
Data Index: 4524438 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.9483. Min Act: -0.1700
Data Index: 755485 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.9483. Min Act: -0.1700
Data Index: 5916552 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.9483. Min Act: -0.1700
Data Index: 6935882 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.8858. Min Act: -0.1700
Data Index: 2415061 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.9170. Min Act: -0.1700
Data Index: 5377514 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.8545. Min Act: -0.1700
Data Index: 3784084 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.8545. Min Act: -0.1700
Data Index: 7709230 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.8545. Min Act: -0.1700
Data Index: 2938609 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.8858. Min Act: -0.1700
Data Index: 4834834 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.8233. Min Act: -0.1700
Data Index: 2044011 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3858. Min Range: -6.3858
Max Act: 5.7920. Min Act: -0.1700
Data Index: 5970372 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19