Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.3324. Min Act: -0.1700
Data Index: 4306197 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2853. Min Act: -0.1700
Data Index: 1456422 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2696. Min Act: -0.1700
Data Index: 6668333 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2225. Min Act: -0.1700
Data Index: 150791 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2382. Min Act: -0.1700
Data Index: 7379048 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2225. Min Act: -0.1700
Data Index: 2116222 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2539. Min Act: -0.1700
Data Index: 5295482 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2382. Min Act: -0.1700
Data Index: 917548 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2225. Min Act: -0.1700
Data Index: 7589342 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.2382. Min Act: -0.1700
Data Index: 5016046 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1910. Min Act: -0.1700
Data Index: 3860179 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1910. Min Act: -0.1700
Data Index: 2557340 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1595. Min Act: -0.1700
Data Index: 4412129 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1910. Min Act: -0.1700
Data Index: 3965309 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1595. Min Act: -0.1700
Data Index: 3411242 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1910. Min Act: -0.1700
Data Index: 7213330 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1595. Min Act: -0.1700
Data Index: 6387428 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1595. Min Act: -0.1700
Data Index: 3704331 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1753. Min Act: -0.1700
Data Index: 3901596 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3324. Min Range: -3.3324
Max Act: 3.1595. Min Act: -0.1700
Data Index: 5413565 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19