Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 144 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.4287. Min Act: -0.1700
Data Index: 6284717 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.3935. Min Act: -0.1700
Data Index: 5731620 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.3759. Min Act: -0.1700
Data Index: 8171509 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.3759. Min Act: -0.1700
Data Index: 7106164 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.3406. Min Act: -0.1700
Data Index: 2589092 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.3053. Min Act: -0.1700
Data Index: 4643438 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.3053. Min Act: -0.1699
Data Index: 3065897 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.3053. Min Act: -0.1700
Data Index: 208423 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.2701. Min Act: -0.1700
Data Index: 6779930 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.2348. Min Act: -0.1700
Data Index: 975128 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.2084. Min Act: -0.1700
Data Index: 6853065 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1996. Min Act: -0.1700
Data Index: 6616351 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1908. Min Act: -0.1700
Data Index: 5608115 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1908. Min Act: -0.1700
Data Index: 3461953 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1820. Min Act: -0.1700
Data Index: 6616352 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1732. Min Act: -0.1698
Data Index: 2227210 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1468. Min Act: -0.1700
Data Index: 3848851 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1468. Min Act: -0.1700
Data Index: 756013 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1468. Min Act: -0.1699
Data Index: 1568880 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4287. Min Range: -1.4287
Max Act: 1.1468. Min Act: -0.1700
Data Index: 3051047 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19