Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.6811. Min Act: -0.1700
Data Index: 6857833 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.5249. Min Act: -0.1700
Data Index: 7865083 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.4936. Min Act: -0.1700
Data Index: 4284476 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.3686. Min Act: -0.1700
Data Index: 1229356 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.3374. Min Act: -0.1700
Data Index: 7346101 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.2436. Min Act: -0.1700
Data Index: 8328672 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.1499. Min Act: -0.1700
Data Index: 1448032 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.0561. Min Act: -0.1700
Data Index: 6815950 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.0561. Min Act: -0.1700
Data Index: 3712870 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.0561. Min Act: -0.1700
Data Index: 7818426 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.0249. Min Act: -0.1700
Data Index: 4878714 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6811. Min Range: -5.6811
Max Act: 5.0249. Min Act: -0.1700
Data Index: 2729325 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6811. Min Range: -5.6811
Max Act: 4.9936. Min Act: -0.1700
Data Index: 6993137 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6811. Min Range: -5.6811
Max Act: 4.9936. Min Act: -0.1700
Data Index: 382943 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6811. Min Range: -5.6811
Max Act: 4.9936. Min Act: -0.1700
Data Index: 657905 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6811. Min Range: -5.6811
Max Act: 4.9936. Min Act: -0.1700
Data Index: 7403803 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6811. Min Range: -5.6811
Max Act: 4.9624. Min Act: -0.1700
Data Index: 2490820 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6811. Min Range: -5.6811
Max Act: 4.9311. Min Act: -0.1700
Data Index: 3297140 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6811. Min Range: -5.6811
Max Act: 4.9624. Min Act: -0.1700
Data Index: 7740726 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6811. Min Range: -5.6811
Max Act: 4.9936. Min Act: -0.1700
Data Index: 278600 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19