Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.3223. Min Act: -0.1700
Data Index: 863860 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.2910. Min Act: -0.1700
Data Index: 6197334 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.1973. Min Act: -0.1700
Data Index: 4877939 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.1035. Min Act: -0.1700
Data Index: 7216123 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0723. Min Act: -0.1700
Data Index: 6314856 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0410. Min Act: -0.1700
Data Index: 4033027 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3223. Min Range: -6.3223
Max Act: 6.0098. Min Act: -0.1700
Data Index: 1783450 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.9160. Min Act: -0.1700
Data Index: 3438478 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.9160. Min Act: -0.1700
Data Index: 4435627 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8848. Min Act: -0.1700
Data Index: 223576 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8848. Min Act: -0.1700
Data Index: 4888915 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8535. Min Act: -0.1700
Data Index: 7241983 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8848. Min Act: -0.1700
Data Index: 1519303 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8848. Min Act: -0.1700
Data Index: 6704085 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8848. Min Act: -0.1700
Data Index: 5789387 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8535. Min Act: -0.1700
Data Index: 2291005 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8535. Min Act: -0.1700
Data Index: 1478064 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8535. Min Act: -0.1700
Data Index: 2734986 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8535. Min Act: -0.1700
Data Index: 132772 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3223. Min Range: -6.3223
Max Act: 5.8535. Min Act: -0.1700
Data Index: 7953307 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19