Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6617. Min Range: -8.6617
Max Act: 8.6617. Min Act: -0.1700
Data Index: 276696 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6617. Min Range: -8.6617
Max Act: 8.5367. Min Act: -0.1700
Data Index: 7688767 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6617. Min Range: -8.6617
Max Act: 8.1617. Min Act: -0.1700
Data Index: 2773610 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6617. Min Range: -8.6617
Max Act: 8.0367. Min Act: -0.1700
Data Index: 4568207 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6617. Min Range: -8.6617
Max Act: 8.0992. Min Act: -0.1700
Data Index: 2805795 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6617. Min Range: -8.6617
Max Act: 8.0367. Min Act: -0.1700
Data Index: 6266536 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.9117. Min Act: -0.1700
Data Index: 5369230 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.9742. Min Act: -0.1700
Data Index: 2191323 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.9742. Min Act: -0.1700
Data Index: 5706841 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.9742. Min Act: -0.1700
Data Index: 3931266 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.8492. Min Act: -0.1700
Data Index: 955038 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.9117. Min Act: -0.1700
Data Index: 8663023 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.9117. Min Act: -0.1700
Data Index: 4376217 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.9117. Min Act: -0.1700
Data Index: 318742 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.8492. Min Act: -0.1700
Data Index: 1866611 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.8492. Min Act: -0.1700
Data Index: 496109 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.8492. Min Act: -0.1700
Data Index: 1850719 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.8492. Min Act: -0.1700
Data Index: 5765817 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.8492. Min Act: -0.1700
Data Index: 4680347 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6617. Min Range: -8.6617
Max Act: 7.7867. Min Act: -0.1700
Data Index: 3272676 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19