Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6344 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2338. Min Range: -8.2338
Max Act: 8.2338. Min Act: -0.1700
Data Index: 6042312 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2338. Min Range: -8.2338
Max Act: 8.2338. Min Act: -0.1700
Data Index: 5724768 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2338. Min Range: -8.2338
Max Act: 8.0463. Min Act: -0.1700
Data Index: 1186286 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.9838. Min Act: -0.1700
Data Index: 2509346 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.9213. Min Act: -0.1700
Data Index: 7798826 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.8588. Min Act: -0.1700
Data Index: 6291166 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.7963. Min Act: -0.1700
Data Index: 1218317 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.7963. Min Act: -0.1700
Data Index: 7424318 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.7338. Min Act: -0.1700
Data Index: 2854956 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.7338. Min Act: -0.1700
Data Index: 4177673 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.7338. Min Act: -0.1700
Data Index: 1002026 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.6713. Min Act: -0.1700
Data Index: 1162618 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.6713. Min Act: -0.1700
Data Index: 2530340 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.7338. Min Act: -0.1700
Data Index: 1620930 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.6713. Min Act: -0.1700
Data Index: 5990938 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.6088. Min Act: -0.1700
Data Index: 4361068 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.6088. Min Act: -0.1700
Data Index: 180974 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.6713. Min Act: -0.1700
Data Index: 8445433 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.5463. Min Act: -0.1700
Data Index: 22312 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2338. Min Range: -8.2338
Max Act: 7.5463. Min Act: -0.1700
Data Index: 3378536 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19