Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1375 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.3728. Min Act: -0.1700
Data Index: 4921425 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.2165. Min Act: -0.1700
Data Index: 40870 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.1540. Min Act: -0.1700
Data Index: 3229445 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.0915. Min Act: -0.1700
Data Index: 443943 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3728. Min Range: -7.3728
Max Act: 7.0290. Min Act: -0.1700
Data Index: 7522844 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9665. Min Act: -0.1700
Data Index: 1338845 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9040. Min Act: -0.1700
Data Index: 8728592 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.9040. Min Act: -0.1700
Data Index: 3561567 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.8728. Min Act: -0.1700
Data Index: 5275636 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.8728. Min Act: -0.1700
Data Index: 430403 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.8415. Min Act: -0.1700
Data Index: 2552105 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.8415. Min Act: -0.1700
Data Index: 1069769 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.8103. Min Act: -0.1700
Data Index: 5595036 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.7790. Min Act: -0.1700
Data Index: 2709968 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.7478. Min Act: -0.1700
Data Index: 4398572 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.7165. Min Act: -0.1700
Data Index: 6754344 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.6853. Min Act: -0.1700
Data Index: 3608027 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.7165. Min Act: -0.1700
Data Index: 941187 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.7165. Min Act: -0.1700
Data Index: 3831632 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3728. Min Range: -7.3728
Max Act: 6.6853. Min Act: -0.1700
Data Index: 2742158 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19