Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4222 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.4011. Min Act: -0.1700
Data Index: 2327271 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.3699. Min Act: -0.1700
Data Index: 1215885 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.3386. Min Act: -0.1700
Data Index: 7686602 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.3386. Min Act: -0.1700
Data Index: 6606277 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.3074. Min Act: -0.1700
Data Index: 3336812 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.3074. Min Act: -0.1700
Data Index: 3107561 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.2449. Min Act: -0.1700
Data Index: 4823431 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.2136. Min Act: -0.1700
Data Index: 4121885 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.1824. Min Act: -0.1700
Data Index: 7158641 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.1824. Min Act: -0.1700
Data Index: 1429550 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.1511. Min Act: -0.1700
Data Index: 4363034 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0886. Min Act: -0.1700
Data Index: 2414858 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0886. Min Act: -0.1700
Data Index: 3276842 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0886. Min Act: -0.1700
Data Index: 72859 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0574. Min Act: -0.1700
Data Index: 5775240 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0261. Min Act: -0.1700
Data Index: 891443 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0261. Min Act: -0.1700
Data Index: 6386993 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0261. Min Act: -0.1700
Data Index: 8732791 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0261. Min Act: -0.1700
Data Index: 2145864 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4011. Min Range: -6.4011
Max Act: 6.0261. Min Act: -0.1700
Data Index: 4683986 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19