Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6398 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0893. Min Range: -8.0893
Max Act: 8.0893. Min Act: -0.1700
Data Index: 6150876 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0893. Min Range: -8.0893
Max Act: 8.0268. Min Act: -0.1700
Data Index: 5385785 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.9643. Min Act: -0.1700
Data Index: 1656938 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.8080. Min Act: -0.1700
Data Index: 101896 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.7455. Min Act: -0.1700
Data Index: 5465671 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.7455. Min Act: -0.1700
Data Index: 2026813 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6830. Min Act: -0.1700
Data Index: 7055886 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6830. Min Act: -0.1700
Data Index: 7886300 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6830. Min Act: -0.1700
Data Index: 1135750 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6518. Min Act: -0.1700
Data Index: 5999515 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6830. Min Act: -0.1700
Data Index: 3007591 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6518. Min Act: -0.1700
Data Index: 55204 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6205. Min Act: -0.1700
Data Index: 1613195 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.5893. Min Act: -0.1700
Data Index: 2196021 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6205. Min Act: -0.1700
Data Index: 1853873 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.6205. Min Act: -0.1700
Data Index: 2370669 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.5893. Min Act: -0.1700
Data Index: 3793998 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.5893. Min Act: -0.1700
Data Index: 1883427 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.5893. Min Act: -0.1700
Data Index: 120332 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0893. Min Range: -8.0893
Max Act: 7.5580. Min Act: -0.1700
Data Index: 6894648 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19