Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2841 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.3912. Min Act: -0.1700
Data Index: 3496141 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.1724. Min Act: -0.1700
Data Index: 4337302 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.1099. Min Act: -0.1700
Data Index: 8673080 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.0787. Min Act: -0.1700
Data Index: 7735834 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3912. Min Range: -6.3912
Max Act: 6.0162. Min Act: -0.1700
Data Index: 98466 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9537. Min Act: -0.1700
Data Index: 996643 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9224. Min Act: -0.1700
Data Index: 4869742 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.9537. Min Act: -0.1700
Data Index: 3151180 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8599. Min Act: -0.1700
Data Index: 237604 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8912. Min Act: -0.1700
Data Index: 4954608 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8912. Min Act: -0.1700
Data Index: 30404 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8599. Min Act: -0.1700
Data Index: 5242433 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8599. Min Act: -0.1700
Data Index: 7653036 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8287. Min Act: -0.1700
Data Index: 1501059 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.7974. Min Act: -0.1700
Data Index: 5385012 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.8287. Min Act: -0.1700
Data Index: 619483 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.7974. Min Act: -0.1700
Data Index: 621545 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.7974. Min Act: -0.1700
Data Index: 5225264 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.7974. Min Act: -0.1700
Data Index: 7813318 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3912. Min Range: -6.3912
Max Act: 5.7662. Min Act: -0.1700
Data Index: 5472331 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19