Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6363 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.7636. Min Act: -0.1700
Data Index: 5261048 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.4824. Min Act: -0.1700
Data Index: 8048192 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.2636. Min Act: -0.1700
Data Index: 3930844 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.2011. Min Act: -0.1700
Data Index: 3160857 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.1386. Min Act: -0.1700
Data Index: 1963299 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.1386. Min Act: -0.1700
Data Index: 6995029 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.1074. Min Act: -0.1700
Data Index: 2469990 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.0761. Min Act: -0.1700
Data Index: 7126613 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.9824. Min Act: -0.1700
Data Index: 1114361 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7636. Min Range: -7.7636
Max Act: 7.0136. Min Act: -0.1700
Data Index: 8174509 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.8886. Min Act: -0.1700
Data Index: 438155 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.8886. Min Act: -0.1700
Data Index: 4741734 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.9199. Min Act: -0.1700
Data Index: 1468951 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.8886. Min Act: -0.1700
Data Index: 4859422 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.8574. Min Act: -0.1700
Data Index: 5036534 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.8886. Min Act: -0.1700
Data Index: 4357960 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.8261. Min Act: -0.1700
Data Index: 5369173 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.7636. Min Act: -0.1700
Data Index: 5778642 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.7949. Min Act: -0.1700
Data Index: 2502194 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7636. Min Range: -7.7636
Max Act: 6.7636. Min Act: -0.1700
Data Index: 6062564 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19