Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.4678. Min Act: -0.1700
Data Index: 4287162 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.3116. Min Act: -0.1700
Data Index: 8765736 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.2178. Min Act: -0.1700
Data Index: 4555182 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.2491. Min Act: -0.1700
Data Index: 4831381 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.2178. Min Act: -0.1700
Data Index: 6784161 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.1553. Min Act: -0.1700
Data Index: 6603162 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.1553. Min Act: -0.1700
Data Index: 3294499 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.0616. Min Act: -0.1700
Data Index: 5029242 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4678. Min Range: -7.4678
Max Act: 7.0303. Min Act: -0.1700
Data Index: 3084391 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.9678. Min Act: -0.1700
Data Index: 1443724 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.9991. Min Act: -0.1700
Data Index: 3439951 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.9991. Min Act: -0.1700
Data Index: 1900038 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.9991. Min Act: -0.1700
Data Index: 7660212 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.9053. Min Act: -0.1700
Data Index: 7926774 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.9366. Min Act: -0.1700
Data Index: 6728142 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.9678. Min Act: -0.1700
Data Index: 7329547 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.8428. Min Act: -0.1700
Data Index: 115409 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.8116. Min Act: -0.1700
Data Index: 5668755 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.8116. Min Act: -0.1700
Data Index: 3008261 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4678. Min Range: -7.4678
Max Act: 6.7491. Min Act: -0.1700
Data Index: 3846142 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19