Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.4088. Min Act: -0.1700
Data Index: 8051654 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.3150. Min Act: -0.1700
Data Index: 4561397 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.2525. Min Act: -0.1700
Data Index: 6183608 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.2525. Min Act: -0.1700
Data Index: 807380 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.1275. Min Act: -0.1700
Data Index: 2981397 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.1588. Min Act: -0.1700
Data Index: 6339275 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.0650. Min Act: -0.1700
Data Index: 547826 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.0650. Min Act: -0.1700
Data Index: 2514852 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.0650. Min Act: -0.1700
Data Index: 7288958 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.0650. Min Act: -0.1700
Data Index: 6170532 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.0650. Min Act: -0.1700
Data Index: 8800324 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.0025. Min Act: -0.1700
Data Index: 1487284 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4088. Min Range: -7.4088
Max Act: 7.0025. Min Act: -0.1700
Data Index: 2033369 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4088. Min Range: -7.4088
Max Act: 6.9713. Min Act: -0.1700
Data Index: 5402975 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4088. Min Range: -7.4088
Max Act: 6.9088. Min Act: -0.1700
Data Index: 8272830 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4088. Min Range: -7.4088
Max Act: 6.9088. Min Act: -0.1700
Data Index: 6835690 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4088. Min Range: -7.4088
Max Act: 6.9088. Min Act: -0.1700
Data Index: 6478753 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4088. Min Range: -7.4088
Max Act: 6.9088. Min Act: -0.1700
Data Index: 6364580 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4088. Min Range: -7.4088
Max Act: 6.9088. Min Act: -0.1700
Data Index: 2514853 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4088. Min Range: -7.4088
Max Act: 6.8775. Min Act: -0.1700
Data Index: 5611684 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19