Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4962 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3656. Min Range: -8.3656
Max Act: 8.3656. Min Act: -0.1700
Data Index: 7729572 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3656. Min Range: -8.3656
Max Act: 8.3031. Min Act: -0.1700
Data Index: 3692292 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3656. Min Range: -8.3656
Max Act: 8.3031. Min Act: -0.1700
Data Index: 3234213 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3656. Min Range: -8.3656
Max Act: 8.1781. Min Act: -0.1700
Data Index: 3599053 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3656. Min Range: -8.3656
Max Act: 8.0531. Min Act: -0.1700
Data Index: 852419 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3656. Min Range: -8.3656
Max Act: 8.0531. Min Act: -0.1700
Data Index: 5238081 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.9906. Min Act: -0.1700
Data Index: 8572056 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.9281. Min Act: -0.1700
Data Index: 371307 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.9906. Min Act: -0.1700
Data Index: 6657219 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.9281. Min Act: -0.1700
Data Index: 138001 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.9906. Min Act: -0.1700
Data Index: 1185303 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.8656. Min Act: -0.1700
Data Index: 4898518 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.8656. Min Act: -0.1700
Data Index: 7006763 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.8656. Min Act: -0.1700
Data Index: 6863663 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.8656. Min Act: -0.1700
Data Index: 5399856 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.8656. Min Act: -0.1700
Data Index: 4389562 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.8031. Min Act: -0.1700
Data Index: 2763309 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.8031. Min Act: -0.1700
Data Index: 7139697 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.6781. Min Act: -0.1700
Data Index: 1178413 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3656. Min Range: -8.3656
Max Act: 7.7406. Min Act: -0.1700
Data Index: 3095834 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19