Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.7617. Min Act: -0.1700
Data Index: 2982771 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.5117. Min Act: -0.1700
Data Index: 5119607 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.5117. Min Act: -0.1700
Data Index: 5711759 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.4492. Min Act: -0.1700
Data Index: 4258739 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.3867. Min Act: -0.1700
Data Index: 5534183 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.2617. Min Act: -0.1700
Data Index: 4946013 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.1992. Min Act: -0.1700
Data Index: 5534180 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.1367. Min Act: -0.1700
Data Index: 7332734 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.1992. Min Act: -0.1700
Data Index: 2900954 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.1992. Min Act: -0.1700
Data Index: 8281315 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.0117. Min Act: -0.1700
Data Index: 1840006 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7617. Min Range: -9.7617
Max Act: 8.9492. Min Act: -0.1700
Data Index: 8338906 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7617. Min Range: -9.7617
Max Act: 9.0117. Min Act: -0.1700
Data Index: 2729958 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7617. Min Range: -9.7617
Max Act: 8.8242. Min Act: -0.1700
Data Index: 3810217 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7617. Min Range: -9.7617
Max Act: 8.8242. Min Act: -0.1700
Data Index: 6569208 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7617. Min Range: -9.7617
Max Act: 8.8242. Min Act: -0.1700
Data Index: 6841040 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7617. Min Range: -9.7617
Max Act: 8.8242. Min Act: -0.1700
Data Index: 2871172 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7617. Min Range: -9.7617
Max Act: 8.7617. Min Act: -0.1700
Data Index: 8060000 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7617. Min Range: -9.7617
Max Act: 8.7617. Min Act: -0.1700
Data Index: 6081070 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7617. Min Range: -9.7617
Max Act: 8.7617. Min Act: -0.1700
Data Index: 5034235 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19