Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.2255. Min Act: -0.1700
Data Index: 6115784 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.2255. Min Act: -0.1700
Data Index: 8197843 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.1318. Min Act: -0.1700
Data Index: 2761059 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.1318. Min Act: -0.1700
Data Index: 216841 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.1005. Min Act: -0.1700
Data Index: 5375794 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.1005. Min Act: -0.1700
Data Index: 7437246 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0693. Min Act: -0.1700
Data Index: 6255330 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0693. Min Act: -0.1700
Data Index: 5845791 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0693. Min Act: -0.1700
Data Index: 8003141 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0380. Min Act: -0.1700
Data Index: 2769327 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0068. Min Act: -0.1700
Data Index: 899732 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0068. Min Act: -0.1700
Data Index: 543169 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0068. Min Act: -0.1700
Data Index: 8197837 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0068. Min Act: -0.1700
Data Index: 3547039 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0068. Min Act: -0.1700
Data Index: 4548385 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2255. Min Range: -5.2255
Max Act: 5.0068. Min Act: -0.1700
Data Index: 1659117 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2255. Min Range: -5.2255
Max Act: 4.9755. Min Act: -0.1700
Data Index: 2635189 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2255. Min Range: -5.2255
Max Act: 4.9443. Min Act: -0.1700
Data Index: 5141228 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2255. Min Range: -5.2255
Max Act: 4.9443. Min Act: -0.1700
Data Index: 5673965 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2255. Min Range: -5.2255
Max Act: 4.9443. Min Act: -0.1700
Data Index: 1718560 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19