Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5675 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.6948. Min Act: -0.1700
Data Index: 4478923 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.6948. Min Act: -0.1700
Data Index: 201909 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.6323. Min Act: -0.1700
Data Index: 49560 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.6635. Min Act: -0.1700
Data Index: 6731189 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.6323. Min Act: -0.1700
Data Index: 7368549 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.5698. Min Act: -0.1700
Data Index: 1680810 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.5385. Min Act: -0.1700
Data Index: 6804188 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.5385. Min Act: -0.1700
Data Index: 5908821 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.5698. Min Act: -0.1700
Data Index: 295529 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.4760. Min Act: -0.1700
Data Index: 5319634 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.4760. Min Act: -0.1700
Data Index: 4681586 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.3510. Min Act: -0.1700
Data Index: 6787180 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.3823. Min Act: -0.1700
Data Index: 6524055 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.3510. Min Act: -0.1700
Data Index: 7795133 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.3510. Min Act: -0.1700
Data Index: 8303906 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.3198. Min Act: -0.1700
Data Index: 7449304 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.3198. Min Act: -0.1700
Data Index: 3814577 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.2885. Min Act: -0.1700
Data Index: 3523416 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.2885. Min Act: -0.1700
Data Index: 6453151 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6948. Min Range: -6.6948
Max Act: 6.3198. Min Act: -0.1700
Data Index: 5185702 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19