Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5434 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.9739. Min Act: -0.1700
Data Index: 8306146 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7864. Min Act: -0.1700
Data Index: 8797016 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7864. Min Act: -0.1700
Data Index: 7698081 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7864. Min Act: -0.1700
Data Index: 1011845 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7552. Min Act: -0.1700
Data Index: 6747839 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7864. Min Act: -0.1700
Data Index: 3762609 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7552. Min Act: -0.1700
Data Index: 3695766 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7552. Min Act: -0.1700
Data Index: 2147300 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7239. Min Act: -0.1700
Data Index: 7328363 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.7239. Min Act: -0.1700
Data Index: 8504470 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.6927. Min Act: -0.1700
Data Index: 2801220 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.6927. Min Act: -0.1700
Data Index: 6878352 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.6614. Min Act: -0.1700
Data Index: 7268456 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.6927. Min Act: -0.1700
Data Index: 5765114 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.6927. Min Act: -0.1700
Data Index: 6932528 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.6302. Min Act: -0.1700
Data Index: 7462612 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.5677. Min Act: -0.1700
Data Index: 6824300 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.5677. Min Act: -0.1700
Data Index: 4781474 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.5677. Min Act: -0.1700
Data Index: 1634969 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9739. Min Range: -6.9739
Max Act: 6.5989. Min Act: -0.1700
Data Index: 601195 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19