Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.2758. Min Act: -0.1700
Data Index: 5756031 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.1821. Min Act: -0.1700
Data Index: 5627925 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.2133. Min Act: -0.1700
Data Index: 2687042 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.1196. Min Act: -0.1700
Data Index: 7845763 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.1196. Min Act: -0.1700
Data Index: 2305040 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.0883. Min Act: -0.1700
Data Index: 1463173 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.0571. Min Act: -0.1700
Data Index: 7548541 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.0258. Min Act: -0.1700
Data Index: 3865142 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.0258. Min Act: -0.1700
Data Index: 3865143 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.0258. Min Act: -0.1700
Data Index: 1392148 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2758. Min Range: -5.2758
Max Act: 5.0258. Min Act: -0.1700
Data Index: 317166 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9946. Min Act: -0.1700
Data Index: 1035884 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9946. Min Act: -0.1700
Data Index: 7509216 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9633. Min Act: -0.1700
Data Index: 7505153 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9946. Min Act: -0.1700
Data Index: 6548301 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9633. Min Act: -0.1700
Data Index: 3865141 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9633. Min Act: -0.1700
Data Index: 2900158 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9633. Min Act: -0.1700
Data Index: 8259701 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9633. Min Act: -0.1700
Data Index: 6381494 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2758. Min Range: -5.2758
Max Act: 4.9321. Min Act: -0.1700
Data Index: 893765 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19