Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3708. Min Act: -0.1700
Data Index: 3446271 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3551. Min Act: -0.1700
Data Index: 8455040 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3551. Min Act: -0.1700
Data Index: 2030139 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3551. Min Act: -0.1700
Data Index: 1845018 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3238. Min Act: -0.1700
Data Index: 6425773 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3238. Min Act: -0.1700
Data Index: 8122645 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3238. Min Act: -0.1700
Data Index: 3197216 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3238. Min Act: -0.1700
Data Index: 4870873 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3081. Min Act: -0.1700
Data Index: 5273819 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3081. Min Act: -0.1700
Data Index: 5140704 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3081. Min Act: -0.1700
Data Index: 4912261 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3081. Min Act: -0.1700
Data Index: 5786223 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3081. Min Act: -0.1700
Data Index: 8816599 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.2924. Min Act: -0.1700
Data Index: 7134617 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.2924. Min Act: -0.1700
Data Index: 7975466 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.3081. Min Act: -0.1700
Data Index: 3243435 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.2924. Min Act: -0.1700
Data Index: 3434859 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.2924. Min Act: -0.1700
Data Index: 851154 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.2924. Min Act: -0.1700
Data Index: 5774630 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3708. Min Range: -3.3708
Max Act: 3.2924. Min Act: -0.1700
Data Index: 4550010 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19