Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2009 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0615. Min Range: -8.0615
Max Act: 8.0615. Min Act: -0.1700
Data Index: 6794847 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.5303. Min Act: -0.1700
Data Index: 5653809 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.4678. Min Act: -0.1700
Data Index: 3181401 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.4365. Min Act: -0.1700
Data Index: 3534943 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.3428. Min Act: -0.1700
Data Index: 1310254 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.3428. Min Act: -0.1700
Data Index: 4697693 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.2490. Min Act: -0.1700
Data Index: 8060202 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.1865. Min Act: -0.1700
Data Index: 2194681 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.2178. Min Act: -0.1700
Data Index: 6154837 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.1240. Min Act: -0.1700
Data Index: 2148304 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.1240. Min Act: -0.1700
Data Index: 6064911 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.0928. Min Act: -0.1700
Data Index: 2235998 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.0928. Min Act: -0.1700
Data Index: 7038749 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.0303. Min Act: -0.1700
Data Index: 5601988 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.0303. Min Act: -0.1700
Data Index: 308454 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0615. Min Range: -8.0615
Max Act: 6.9990. Min Act: -0.1700
Data Index: 2505800 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.0303. Min Act: -0.1700
Data Index: 2908786 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0615. Min Range: -8.0615
Max Act: 7.0303. Min Act: -0.1700
Data Index: 578051 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0615. Min Range: -8.0615
Max Act: 6.9990. Min Act: -0.1700
Data Index: 7882275 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0615. Min Range: -8.0615
Max Act: 6.9990. Min Act: -0.1700
Data Index: 4749542 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19