Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4541 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.6872. Min Act: -0.1700
Data Index: 6603376 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.4997. Min Act: -0.1700
Data Index: 6603375 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.4372. Min Act: -0.1700
Data Index: 309885 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.4059. Min Act: -0.1700
Data Index: 2359460 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.3122. Min Act: -0.1700
Data Index: 294048 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.3122. Min Act: -0.1700
Data Index: 8340069 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.2809. Min Act: -0.1700
Data Index: 980035 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.2809. Min Act: -0.1700
Data Index: 8512747 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.2809. Min Act: -0.1700
Data Index: 5343206 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.2809. Min Act: -0.1700
Data Index: 980036 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.2184. Min Act: -0.1700
Data Index: 3023157 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.2497. Min Act: -0.1700
Data Index: 3821816 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.2184. Min Act: -0.1700
Data Index: 5890961 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.1872. Min Act: -0.1700
Data Index: 2588638 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.1559. Min Act: -0.1700
Data Index: 4969173 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.1559. Min Act: -0.1700
Data Index: 3637188 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.1559. Min Act: -0.1700
Data Index: 5145785 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.1247. Min Act: -0.1700
Data Index: 5873198 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.1247. Min Act: -0.1700
Data Index: 7441600 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6872. Min Range: -5.6872
Max Act: 5.0934. Min Act: -0.1700
Data Index: 8249033 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19