Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1465. Min Range: -7.1465
Max Act: 7.1465. Min Act: -0.1700
Data Index: 1531800 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1465. Min Range: -7.1465
Max Act: 7.1152. Min Act: -0.1700
Data Index: 4404803 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.9277. Min Act: -0.1700
Data Index: 8113395 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.7715. Min Act: -0.1700
Data Index: 7035892 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.6777. Min Act: -0.1700
Data Index: 4747581 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.6465. Min Act: -0.1700
Data Index: 7200930 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.6152. Min Act: -0.1700
Data Index: 4851700 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.6152. Min Act: -0.1700
Data Index: 6383860 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.5840. Min Act: -0.1700
Data Index: 895252 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.5840. Min Act: -0.1700
Data Index: 7390320 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.5527. Min Act: -0.1700
Data Index: 3537046 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.5215. Min Act: -0.1700
Data Index: 7030889 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.5215. Min Act: -0.1700
Data Index: 2887102 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.4590. Min Act: -0.1700
Data Index: 8610750 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.4590. Min Act: -0.1700
Data Index: 1081130 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.4590. Min Act: -0.1700
Data Index: 4562960 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.4277. Min Act: -0.1700
Data Index: 6094119 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.4277. Min Act: -0.1700
Data Index: 4075426 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.3652. Min Act: -0.1700
Data Index: 3761017 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1465. Min Range: -7.1465
Max Act: 6.3965. Min Act: -0.1700
Data Index: 6061059 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19