Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.6895. Min Act: -0.1700
Data Index: 7476814 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.6270. Min Act: -0.1700
Data Index: 6392562 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.5020. Min Act: -0.1700
Data Index: 8639969 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.3770. Min Act: -0.1700
Data Index: 1560985 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.2520. Min Act: -0.1700
Data Index: 6366903 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.0957. Min Act: -0.1700
Data Index: 7748440 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.2520. Min Act: -0.1700
Data Index: 2891347 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.1270. Min Act: -0.1700
Data Index: 3825334 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.1270. Min Act: -0.1700
Data Index: 6298192 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.0957. Min Act: -0.1700
Data Index: 216767 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.0332. Min Act: -0.1700
Data Index: 8722523 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.0645. Min Act: -0.1700
Data Index: 1219335 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.0020. Min Act: -0.1700
Data Index: 4265923 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6895. Min Range: -8.6895
Max Act: 7.9707. Min Act: -0.1700
Data Index: 7078901 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.0020. Min Act: -0.1700
Data Index: 8152209 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6895. Min Range: -8.6895
Max Act: 7.9707. Min Act: -0.1700
Data Index: 7523595 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6895. Min Range: -8.6895
Max Act: 7.9082. Min Act: -0.1700
Data Index: 8685597 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6895. Min Range: -8.6895
Max Act: 7.9707. Min Act: -0.1700
Data Index: 2973372 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6895. Min Range: -8.6895
Max Act: 7.9707. Min Act: -0.1700
Data Index: 8656174 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6895. Min Range: -8.6895
Max Act: 8.0020. Min Act: -0.1700
Data Index: 2001650 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19