Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 631 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.4550. Min Act: -0.1700
Data Index: 2118056 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.3612. Min Act: -0.1700
Data Index: 5129242 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.3300. Min Act: -0.1700
Data Index: 5114170 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.2675. Min Act: -0.1700
Data Index: 6590922 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.2362. Min Act: -0.1700
Data Index: 521944 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.2675. Min Act: -0.1700
Data Index: 1099238 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.2362. Min Act: -0.1700
Data Index: 3117474 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.2362. Min Act: -0.1700
Data Index: 6728955 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.2050. Min Act: -0.1700
Data Index: 4175328 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.1737. Min Act: -0.1700
Data Index: 7467053 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.1425. Min Act: -0.1700
Data Index: 7134920 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.1112. Min Act: -0.1700
Data Index: 8118550 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.1112. Min Act: -0.1700
Data Index: 1885802 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.0800. Min Act: -0.1700
Data Index: 646368 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.0800. Min Act: -0.1700
Data Index: 3050600 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.1112. Min Act: -0.1700
Data Index: 4824191 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.0800. Min Act: -0.1700
Data Index: 4202095 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.0800. Min Act: -0.1700
Data Index: 3879861 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.0800. Min Act: -0.1700
Data Index: 752287 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4550. Min Range: -5.4550
Max Act: 5.0487. Min Act: -0.1700
Data Index: 3973835 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19