Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.9246. Min Act: -0.1700
Data Index: 3872776 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.8934. Min Act: -0.1700
Data Index: 8342384 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7996. Min Act: -0.1700
Data Index: 6915268 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7371. Min Act: -0.1700
Data Index: 5914597 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7371. Min Act: -0.1700
Data Index: 3340235 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7371. Min Act: -0.1700
Data Index: 4595693 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7059. Min Act: -0.1700
Data Index: 1539101 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.7059. Min Act: -0.1700
Data Index: 8569325 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.6434. Min Act: -0.1700
Data Index: 4826601 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.6434. Min Act: -0.1700
Data Index: 310618 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.6121. Min Act: -0.1700
Data Index: 1208208 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.6121. Min Act: -0.1700
Data Index: 4861667 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.5809. Min Act: -0.1700
Data Index: 1324761 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.5809. Min Act: -0.1700
Data Index: 3881211 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.6121. Min Act: -0.1700
Data Index: 368322 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.5809. Min Act: -0.1700
Data Index: 2458216 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.5496. Min Act: -0.1700
Data Index: 2564500 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.5496. Min Act: -0.1700
Data Index: 942751 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.5184. Min Act: -0.1700
Data Index: 2458214 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9246. Min Range: -5.9246
Max Act: 5.5184. Min Act: -0.1700
Data Index: 1789544 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19