Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1262 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.4157. Min Act: -0.1700
Data Index: 163478 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.3532. Min Act: -0.1700
Data Index: 3454942 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.2907. Min Act: -0.1700
Data Index: 7584362 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.2594. Min Act: -0.1700
Data Index: 7771385 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.1344. Min Act: -0.1700
Data Index: 6132320 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.0719. Min Act: -0.1700
Data Index: 1780119 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.0719. Min Act: -0.1700
Data Index: 7398471 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.0719. Min Act: -0.1700
Data Index: 4180907 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.0407. Min Act: -0.1700
Data Index: 8622446 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.0407. Min Act: -0.1700
Data Index: 7747023 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.0094. Min Act: -0.1700
Data Index: 7132675 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.0094. Min Act: -0.1700
Data Index: 431241 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4157. Min Range: -5.4157
Max Act: 4.9469. Min Act: -0.1700
Data Index: 4042587 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4157. Min Range: -5.4157
Max Act: 4.9781. Min Act: -0.1700
Data Index: 4180905 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4157. Min Range: -5.4157
Max Act: 4.9781. Min Act: -0.1700
Data Index: 3753878 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4157. Min Range: -5.4157
Max Act: 4.9781. Min Act: -0.1700
Data Index: 1503649 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4157. Min Range: -5.4157
Max Act: 5.0094. Min Act: -0.1700
Data Index: 1942102 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4157. Min Range: -5.4157
Max Act: 4.9469. Min Act: -0.1700
Data Index: 6039268 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4157. Min Range: -5.4157
Max Act: 4.9781. Min Act: -0.1700
Data Index: 146396 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4157. Min Range: -5.4157
Max Act: 4.9469. Min Act: -0.1700
Data Index: 2732385 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19