Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.8957. Min Act: -0.1700
Data Index: 7299872 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.8331. Min Act: -0.1700
Data Index: 6613932 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.8019. Min Act: -0.1700
Data Index: 6840421 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.8331. Min Act: -0.1700
Data Index: 1076468 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.7393. Min Act: -0.1700
Data Index: 84346 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.7393. Min Act: -0.1700
Data Index: 4484926 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.7393. Min Act: -0.1700
Data Index: 8575823 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.7393. Min Act: -0.1700
Data Index: 7592015 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.6611. Min Act: -0.1700
Data Index: 4145221 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.6767. Min Act: -0.1700
Data Index: 2268410 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.6611. Min Act: -0.1700
Data Index: 7669508 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.6454. Min Act: -0.1700
Data Index: 6160165 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.5985. Min Act: -0.1700
Data Index: 7755226 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.6141. Min Act: -0.1700
Data Index: 4865477 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.5672. Min Act: -0.1700
Data Index: 8093664 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.6298. Min Act: -0.1700
Data Index: 6568028 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.5672. Min Act: -0.1700
Data Index: 1091283 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.5985. Min Act: -0.1700
Data Index: 7020151 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.5515. Min Act: -0.1700
Data Index: 3128109 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8957. Min Range: -3.8957
Max Act: 3.5359. Min Act: -0.1700
Data Index: 5950565 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19