Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3557. Min Range: -6.3557
Max Act: 6.3557. Min Act: -0.1700
Data Index: 4322396 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.7932. Min Act: -0.1700
Data Index: 3422582 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.7932. Min Act: -0.1700
Data Index: 6014173 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.7307. Min Act: -0.1700
Data Index: 2716000 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.6682. Min Act: -0.1700
Data Index: 6348499 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.6682. Min Act: -0.1700
Data Index: 5229109 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.6682. Min Act: -0.1700
Data Index: 3522245 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.6057. Min Act: -0.1700
Data Index: 4415418 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.5745. Min Act: -0.1700
Data Index: 4246339 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.5120. Min Act: -0.1700
Data Index: 8789016 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.4495. Min Act: -0.1700
Data Index: 1506448 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 3194762 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 7335041 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 6068604 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.4495. Min Act: -0.1700
Data Index: 7176897 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.3870. Min Act: -0.1700
Data Index: 3898480 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.3870. Min Act: -0.1700
Data Index: 7100196 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.3870. Min Act: -0.1700
Data Index: 2731557 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.3870. Min Act: -0.1700
Data Index: 2567741 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3557. Min Range: -6.3557
Max Act: 5.3557. Min Act: -0.1700
Data Index: 1800890 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19