Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3043 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0631. Min Range: -5.0631
Max Act: 5.0631. Min Act: -0.1700
Data Index: 2756744 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.9381. Min Act: -0.1700
Data Index: 6179663 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.7819. Min Act: -0.1700
Data Index: 528195 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.7819. Min Act: -0.1700
Data Index: 564370 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.7819. Min Act: -0.1700
Data Index: 6622814 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.7506. Min Act: -0.1700
Data Index: 5939932 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.7194. Min Act: -0.1700
Data Index: 6525508 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.7194. Min Act: -0.1700
Data Index: 7874118 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.7194. Min Act: -0.1700
Data Index: 395594 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.6881. Min Act: -0.1700
Data Index: 7106388 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.6569. Min Act: -0.1700
Data Index: 4415503 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.6256. Min Act: -0.1700
Data Index: 3746317 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.6256. Min Act: -0.1700
Data Index: 4529727 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.5944. Min Act: -0.1700
Data Index: 8694616 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.6256. Min Act: -0.1700
Data Index: 4257340 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.5944. Min Act: -0.1700
Data Index: 4463177 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.5631. Min Act: -0.1700
Data Index: 401038 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.5631. Min Act: -0.1700
Data Index: 4362627 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.5319. Min Act: -0.1700
Data Index: 6382873 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0631. Min Range: -5.0631
Max Act: 4.5319. Min Act: -0.1700
Data Index: 6428692 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19