Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1494 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2898. Min Act: -0.1700
Data Index: 3478284 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2898. Min Act: -0.1700
Data Index: 8064128 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2585. Min Act: -0.1700
Data Index: 5646279 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2585. Min Act: -0.1700
Data Index: 5151469 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2585. Min Act: -0.1700
Data Index: 2205283 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2898. Min Act: -0.1700
Data Index: 4367327 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2273. Min Act: -0.1700
Data Index: 1384660 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2273. Min Act: -0.1700
Data Index: 5404622 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2273. Min Act: -0.1700
Data Index: 1690117 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2273. Min Act: -0.1700
Data Index: 2539592 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2273. Min Act: -0.1700
Data Index: 5839894 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.2585. Min Act: -0.1700
Data Index: 8124520 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.1648. Min Act: -0.1700
Data Index: 7717604 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.1960. Min Act: -0.1700
Data Index: 499773 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.1960. Min Act: -0.1700
Data Index: 2882011 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.1335. Min Act: -0.1700
Data Index: 6476480 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.1960. Min Act: -0.1700
Data Index: 1235109 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.1023. Min Act: -0.1700
Data Index: 6805734 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.1335. Min Act: -0.1700
Data Index: 1648154 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2898. Min Range: -4.2898
Max Act: 4.1648. Min Act: -0.1700
Data Index: 699739 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19