Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.4088. Min Act: -0.1700
Data Index: 2190766 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.2213. Min Act: -0.1700
Data Index: 601284 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.1901. Min Act: -0.1700
Data Index: 4976463 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.1901. Min Act: -0.1700
Data Index: 6240265 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.1588. Min Act: -0.1700
Data Index: 1206764 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.0651. Min Act: -0.1700
Data Index: 8488981 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.0338. Min Act: -0.1700
Data Index: 8292834 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.0026. Min Act: -0.1700
Data Index: 1310342 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4088. Min Range: -5.4088
Max Act: 5.0338. Min Act: -0.1700
Data Index: 7723128 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.9401. Min Act: -0.1700
Data Index: 7763861 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.9401. Min Act: -0.1700
Data Index: 6323231 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.9088. Min Act: -0.1700
Data Index: 5680343 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.9088. Min Act: -0.1700
Data Index: 3913542 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.8776. Min Act: -0.1700
Data Index: 6741083 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.8776. Min Act: -0.1700
Data Index: 2450737 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.8776. Min Act: -0.1700
Data Index: 2450735 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.8776. Min Act: -0.1700
Data Index: 3913544 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.8776. Min Act: -0.1700
Data Index: 7042479 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.8463. Min Act: -0.1700
Data Index: 4597855 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4088. Min Range: -5.4088
Max Act: 4.8463. Min Act: -0.1700
Data Index: 6253765 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19