Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.8722. Min Act: -0.1700
Data Index: 201225 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.8253. Min Act: -0.1700
Data Index: 6041268 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.7158. Min Act: -0.1700
Data Index: 2091470 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.6220. Min Act: -0.1700
Data Index: 3595324 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5907. Min Act: -0.1700
Data Index: 3506226 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5593. Min Act: -0.1700
Data Index: 6905911 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5593. Min Act: -0.1700
Data Index: 6458045 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5437. Min Act: -0.1700
Data Index: 2465153 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5437. Min Act: -0.1700
Data Index: 5863061 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5280. Min Act: -0.1700
Data Index: 2031813 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5280. Min Act: -0.1700
Data Index: 1359656 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.4967. Min Act: -0.1700
Data Index: 1296290 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5124. Min Act: -0.1700
Data Index: 819052 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.5124. Min Act: -0.1700
Data Index: 2171685 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.4654. Min Act: -0.1700
Data Index: 4070724 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.4967. Min Act: -0.1700
Data Index: 2116052 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.4810. Min Act: -0.1700
Data Index: 425284 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.4654. Min Act: -0.1700
Data Index: 4897493 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.4497. Min Act: -0.1700
Data Index: 7790740 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8722. Min Range: -3.8722
Max Act: 3.4340. Min Act: -0.1700
Data Index: 4897492 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19