Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.6457. Min Act: -0.1700
Data Index: 1015241 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.4582. Min Act: -0.1700
Data Index: 6120288 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.4270. Min Act: -0.1700
Data Index: 3116725 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3957. Min Act: -0.1700
Data Index: 5702236 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3957. Min Act: -0.1700
Data Index: 7959961 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3957. Min Act: -0.1700
Data Index: 2703746 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3957. Min Act: -0.1700
Data Index: 374626 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3957. Min Act: -0.1700
Data Index: 4837539 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3645. Min Act: -0.1700
Data Index: 884821 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3645. Min Act: -0.1700
Data Index: 7390061 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3957. Min Act: -0.1700
Data Index: 4840461 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3645. Min Act: -0.1700
Data Index: 62898 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3645. Min Act: -0.1700
Data Index: 8276575 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3645. Min Act: -0.1700
Data Index: 7009293 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6181345 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6754309 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3332. Min Act: -0.1700
Data Index: 6696593 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3020. Min Act: -0.1700
Data Index: 4807474 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3332. Min Act: -0.1700
Data Index: 2469723 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6457. Min Range: -6.6457
Max Act: 6.3332. Min Act: -0.1700
Data Index: 4879849 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19