Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.7616. Min Act: -0.1700
Data Index: 2191816 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.7616. Min Act: -0.1700
Data Index: 7865222 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.7303. Min Act: -0.1700
Data Index: 7690603 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6990. Min Act: -0.1700
Data Index: 3437338 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6990. Min Act: -0.1700
Data Index: 8575677 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6521. Min Act: -0.1700
Data Index: 5827032 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6364. Min Act: -0.1700
Data Index: 7002630 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6208. Min Act: -0.1700
Data Index: 7083339 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6051. Min Act: -0.1700
Data Index: 341732 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6051. Min Act: -0.1700
Data Index: 5425294 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6208. Min Act: -0.1700
Data Index: 6079501 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6051. Min Act: -0.1700
Data Index: 522257 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6208. Min Act: -0.1700
Data Index: 5073811 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.5738. Min Act: -0.1700
Data Index: 5389012 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.6051. Min Act: -0.1700
Data Index: 4097083 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.5738. Min Act: -0.1700
Data Index: 2899053 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.5425. Min Act: -0.1700
Data Index: 4140043 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.5582. Min Act: -0.1700
Data Index: 6551077 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.5582. Min Act: -0.1700
Data Index: 5584471 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7616. Min Range: -3.7616
Max Act: 3.5425. Min Act: -0.1700
Data Index: 623335 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19