Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5045 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4824. Min Act: -0.1700
Data Index: 7774357 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.5137. Min Act: -0.1700
Data Index: 5309067 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4824. Min Act: -0.1700
Data Index: 7098362 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4667. Min Act: -0.1700
Data Index: 454379 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4667. Min Act: -0.1700
Data Index: 8037556 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4510. Min Act: -0.1700
Data Index: 5628223 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4197. Min Act: -0.1700
Data Index: 3426626 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4354. Min Act: -0.1700
Data Index: 7933799 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4197. Min Act: -0.1700
Data Index: 5729578 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4354. Min Act: -0.1700
Data Index: 672830 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4040. Min Act: -0.1700
Data Index: 3086614 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.4040. Min Act: -0.1700
Data Index: 5840160 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.3883. Min Act: -0.1700
Data Index: 1294606 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.3883. Min Act: -0.1700
Data Index: 192203 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.3727. Min Act: -0.1700
Data Index: 3448399 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.3883. Min Act: -0.1700
Data Index: 8111594 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.3727. Min Act: -0.1700
Data Index: 6199355 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.3570. Min Act: -0.1700
Data Index: 7968932 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.3570. Min Act: -0.1700
Data Index: 7751721 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5137. Min Range: -3.5137
Max Act: 3.3570. Min Act: -0.1700
Data Index: 1636763 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19