Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4229 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.5305. Min Act: -0.1700
Data Index: 6262747 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.2805. Min Act: -0.1700
Data Index: 4823082 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.2180. Min Act: -0.1700
Data Index: 3260874 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.1867. Min Act: -0.1700
Data Index: 8762151 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.1867. Min Act: -0.1700
Data Index: 6805436 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.1555. Min Act: -0.1700
Data Index: 444491 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.1555. Min Act: -0.1700
Data Index: 2096827 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.1555. Min Act: -0.1700
Data Index: 8335523 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.1242. Min Act: -0.1700
Data Index: 6912267 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5305. Min Range: -7.5305
Max Act: 6.9992. Min Act: -0.1700
Data Index: 3432227 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.0305. Min Act: -0.1700
Data Index: 538167 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.0305. Min Act: -0.1700
Data Index: 7597802 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5305. Min Range: -7.5305
Max Act: 7.0305. Min Act: -0.1700
Data Index: 8818247 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5305. Min Range: -7.5305
Max Act: 6.9680. Min Act: -0.1700
Data Index: 6693669 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5305. Min Range: -7.5305
Max Act: 6.9367. Min Act: -0.1700
Data Index: 2784507 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5305. Min Range: -7.5305
Max Act: 6.9367. Min Act: -0.1700
Data Index: 3076162 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5305. Min Range: -7.5305
Max Act: 6.9680. Min Act: -0.1700
Data Index: 2638529 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5305. Min Range: -7.5305
Max Act: 6.9055. Min Act: -0.1700
Data Index: 5147254 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5305. Min Range: -7.5305
Max Act: 6.8742. Min Act: -0.1700
Data Index: 4510428 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5305. Min Range: -7.5305
Max Act: 6.8742. Min Act: -0.1700
Data Index: 3962943 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19