Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1444 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.2276. Min Act: -0.1700
Data Index: 1341295 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.1338. Min Act: -0.1700
Data Index: 7684981 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.1338. Min Act: -0.1700
Data Index: 951467 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.1025. Min Act: -0.1700
Data Index: 1666913 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.1025. Min Act: -0.1700
Data Index: 6790331 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.0713. Min Act: -0.1700
Data Index: 8186710 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.0088. Min Act: -0.1700
Data Index: 6775259 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.0088. Min Act: -0.1700
Data Index: 446991 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9775. Min Act: -0.1700
Data Index: 7367759 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2276. Min Range: -4.2276
Max Act: 4.0088. Min Act: -0.1700
Data Index: 4234854 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9775. Min Act: -0.1700
Data Index: 6387023 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9462. Min Act: -0.1700
Data Index: 8237835 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9462. Min Act: -0.1700
Data Index: 5589661 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9462. Min Act: -0.1700
Data Index: 6011426 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9462. Min Act: -0.1700
Data Index: 467447 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9462. Min Act: -0.1700
Data Index: 917212 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9150. Min Act: -0.1700
Data Index: 894540 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.9150. Min Act: -0.1700
Data Index: 655308 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.8837. Min Act: -0.1700
Data Index: 5761491 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2276. Min Range: -4.2276
Max Act: 3.8524. Min Act: -0.1700
Data Index: 2785531 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19