Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5807 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.7646. Min Act: -0.1700
Data Index: 7278787 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.5146. Min Act: -0.1700
Data Index: 7278786 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.4209. Min Act: -0.1700
Data Index: 5773751 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.4209. Min Act: -0.1700
Data Index: 1924655 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.3896. Min Act: -0.1700
Data Index: 1122687 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.3896. Min Act: -0.1700
Data Index: 588449 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.3584. Min Act: -0.1700
Data Index: 6624242 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.3584. Min Act: -0.1700
Data Index: 5624941 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.3271. Min Act: -0.1700
Data Index: 8022 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.3271. Min Act: -0.1700
Data Index: 588447 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.3271. Min Act: -0.1700
Data Index: 5797357 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2959. Min Act: -0.1700
Data Index: 3026749 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2959. Min Act: -0.1700
Data Index: 8582508 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2959. Min Act: -0.1700
Data Index: 2569034 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2334. Min Act: -0.1700
Data Index: 997766 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2334. Min Act: -0.1700
Data Index: 3026747 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2646. Min Act: -0.1700
Data Index: 6551752 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2646. Min Act: -0.1700
Data Index: 4089514 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2334. Min Act: -0.1700
Data Index: 4653966 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2334. Min Act: -0.1700
Data Index: 404175 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19