Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3562. Min Range: -9.3562
Max Act: 9.3562. Min Act: -0.1700
Data Index: 6247808 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.8562. Min Act: -0.1700
Data Index: 5544993 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.8562. Min Act: -0.1700
Data Index: 3009657 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.8562. Min Act: -0.1700
Data Index: 8751356 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.7937. Min Act: -0.1700
Data Index: 8349893 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.6687. Min Act: -0.1700
Data Index: 3587361 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.6062. Min Act: -0.1700
Data Index: 1991593 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.5437. Min Act: -0.1700
Data Index: 3826884 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.5437. Min Act: -0.1700
Data Index: 3497670 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.4187. Min Act: -0.1700
Data Index: 5660696 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.3874. Min Act: -0.1700
Data Index: 8171678 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.2937. Min Act: -0.1700
Data Index: 4086200 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.2937. Min Act: -0.1700
Data Index: 8641708 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.2312. Min Act: -0.1700
Data Index: 7407168 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.2624. Min Act: -0.1700
Data Index: 2832396 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.1999. Min Act: -0.1700
Data Index: 3449633 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.1999. Min Act: -0.1700
Data Index: 7105706 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.1999. Min Act: -0.1700
Data Index: 371792 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.1374. Min Act: -0.1700
Data Index: 5612311 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3562. Min Range: -9.3562
Max Act: 8.1687. Min Act: -0.1700
Data Index: 3587360 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19