Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1985. Min Act: -0.1700
Data Index: 6687258 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.2297. Min Act: -0.1700
Data Index: 1510700 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1985. Min Act: -0.1700
Data Index: 8523839 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1672. Min Act: -0.1700
Data Index: 3486832 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1672. Min Act: -0.1700
Data Index: 7015199 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1047. Min Act: -0.1700
Data Index: 7056694 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1047. Min Act: -0.1700
Data Index: 3531545 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1047. Min Act: -0.1700
Data Index: 6232028 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1047. Min Act: -0.1700
Data Index: 5632203 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0422. Min Act: -0.1700
Data Index: 4615484 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.1047. Min Act: -0.1700
Data Index: 8097931 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0734. Min Act: -0.1700
Data Index: 642429 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0734. Min Act: -0.1700
Data Index: 8548252 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0422. Min Act: -0.1700
Data Index: 3600965 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0422. Min Act: -0.1700
Data Index: 3843911 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0422. Min Act: -0.1700
Data Index: 2368365 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0109. Min Act: -0.1700
Data Index: 5829837 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0109. Min Act: -0.1700
Data Index: 7126113 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0109. Min Act: -0.1700
Data Index: 5467091 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2297. Min Range: -4.2297
Max Act: 4.0109. Min Act: -0.1700
Data Index: 8307673 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19