Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4254 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.7825. Min Act: -0.1700
Data Index: 7153306 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.7199. Min Act: -0.1700
Data Index: 3887852 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.7199. Min Act: -0.1700
Data Index: 3285386 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6886. Min Act: -0.1700
Data Index: 5668286 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6886. Min Act: -0.1700
Data Index: 504001 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6886. Min Act: -0.1700
Data Index: 539564 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6886. Min Act: -0.1700
Data Index: 6680018 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6573. Min Act: -0.1700
Data Index: 4248188 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6573. Min Act: -0.1700
Data Index: 7338220 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6573. Min Act: -0.1700
Data Index: 6216430 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6573. Min Act: -0.1700
Data Index: 6111083 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6260. Min Act: -0.1700
Data Index: 4846888 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6260. Min Act: -0.1700
Data Index: 671869 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6260. Min Act: -0.1700
Data Index: 2425884 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6260. Min Act: -0.1700
Data Index: 8206881 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.6260. Min Act: -0.1700
Data Index: 8489052 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.5947. Min Act: -0.1700
Data Index: 1491006 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.5634. Min Act: -0.1700
Data Index: 3335024 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.5947. Min Act: -0.1700
Data Index: 2368206 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7825. Min Range: -3.7825
Max Act: 3.5947. Min Act: -0.1700
Data Index: 773050 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19