Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 494 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.6670. Min Act: -0.1700
Data Index: 5585157 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.4795. Min Act: -0.1700
Data Index: 8195451 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.5420. Min Act: -0.1700
Data Index: 7320116 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.4795. Min Act: -0.1700
Data Index: 7772173 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.4795. Min Act: -0.1700
Data Index: 3017359 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.4170. Min Act: -0.1700
Data Index: 202582 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.2920. Min Act: -0.1700
Data Index: 6642521 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.2920. Min Act: -0.1700
Data Index: 8668579 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.2920. Min Act: -0.1700
Data Index: 4532161 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.2920. Min Act: -0.1700
Data Index: 4967243 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.2920. Min Act: -0.1700
Data Index: 3096585 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.2920. Min Act: -0.1700
Data Index: 2020399 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.2295. Min Act: -0.1700
Data Index: 1711489 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.2295. Min Act: -0.1700
Data Index: 3014422 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.1670. Min Act: -0.1700
Data Index: 4290071 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.1670. Min Act: -0.1700
Data Index: 2597858 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.1670. Min Act: -0.1700
Data Index: 2927990 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.1670. Min Act: -0.1700
Data Index: 7794393 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.1670. Min Act: -0.1700
Data Index: 1802788 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6670. Min Range: -8.6670
Max Act: 8.1670. Min Act: -0.1700
Data Index: 4566666 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19