Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.4023. Min Act: -0.1700
Data Index: 1943212 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.3398. Min Act: -0.1700
Data Index: 6152526 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.2461. Min Act: -0.1700
Data Index: 8188290 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.2461. Min Act: -0.1700
Data Index: 3459181 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.1836. Min Act: -0.1700
Data Index: 8771295 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.1523. Min Act: -0.1700
Data Index: 1829051 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0273. Min Act: -0.1700
Data Index: 6581814 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4023. Min Range: -7.4023
Max Act: 7.0273. Min Act: -0.1700
Data Index: 4310072 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9961. Min Act: -0.1700
Data Index: 5491435 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9961. Min Act: -0.1700
Data Index: 8150096 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9961. Min Act: -0.1700
Data Index: 6112142 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9648. Min Act: -0.1700
Data Index: 5260261 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9336. Min Act: -0.1700
Data Index: 7324716 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.9023. Min Act: -0.1700
Data Index: 5229950 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.8711. Min Act: -0.1700
Data Index: 3805847 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.8711. Min Act: -0.1700
Data Index: 7134003 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.8398. Min Act: -0.1700
Data Index: 3099691 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.7773. Min Act: -0.1700
Data Index: 1360462 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.7461. Min Act: -0.1700
Data Index: 3674452 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4023. Min Range: -7.4023
Max Act: 6.7461. Min Act: -0.1700
Data Index: 4481362 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19