Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2271 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.8965. Min Act: -0.1700
Data Index: 824454 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.8652. Min Act: -0.1700
Data Index: 8433230 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.8340. Min Act: -0.1700
Data Index: 6901716 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.8027. Min Act: -0.1700
Data Index: 2755903 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.8340. Min Act: -0.1700
Data Index: 5110518 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.7715. Min Act: -0.1700
Data Index: 3835595 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.7715. Min Act: -0.1700
Data Index: 3641608 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.6777. Min Act: -0.1700
Data Index: 5627927 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.6777. Min Act: -0.1700
Data Index: 1085124 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.6777. Min Act: -0.1700
Data Index: 6020298 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.6777. Min Act: -0.1700
Data Index: 1826917 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.6465. Min Act: -0.1700
Data Index: 495771 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.6152. Min Act: -0.1700
Data Index: 8686232 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5840. Min Act: -0.1700
Data Index: 6795762 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.6152. Min Act: -0.1700
Data Index: 2856612 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5840. Min Act: -0.1700
Data Index: 4466683 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5840. Min Act: -0.1700
Data Index: 925722 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5840. Min Act: -0.1700
Data Index: 1007197 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5527. Min Act: -0.1700
Data Index: 5051436 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5840. Min Act: -0.1700
Data Index: 2882010 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19