Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1094 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2918. Min Range: -5.2918
Max Act: 5.2918. Min Act: -0.1700
Data Index: 2518797 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2918. Min Range: -5.2918
Max Act: 5.1668. Min Act: -0.1700
Data Index: 2239541 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2918. Min Range: -5.2918
Max Act: 5.1355. Min Act: -0.1700
Data Index: 1857947 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2918. Min Range: -5.2918
Max Act: 5.0730. Min Act: -0.1700
Data Index: 4932455 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2918. Min Range: -5.2918
Max Act: 5.0105. Min Act: -0.1700
Data Index: 3639222 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.9793. Min Act: -0.1700
Data Index: 4640623 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.9480. Min Act: -0.1700
Data Index: 8291301 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.9168. Min Act: -0.1700
Data Index: 919630 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.8855. Min Act: -0.1700
Data Index: 6863588 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.8543. Min Act: -0.1700
Data Index: 1148613 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.8543. Min Act: -0.1700
Data Index: 217125 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.8855. Min Act: -0.1700
Data Index: 134208 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.8543. Min Act: -0.1700
Data Index: 42954 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.7918. Min Act: -0.1700
Data Index: 2026168 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.7918. Min Act: -0.1700
Data Index: 6251951 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.7918. Min Act: -0.1700
Data Index: 4305073 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.7605. Min Act: -0.1700
Data Index: 2912965 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.7918. Min Act: -0.1700
Data Index: 2069518 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.7605. Min Act: -0.1700
Data Index: 3438515 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2918. Min Range: -5.2918
Max Act: 4.7605. Min Act: -0.1700
Data Index: 2981957 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19