Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1687 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.4544. Min Act: -0.1700
Data Index: 5625808 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.3447. Min Act: -0.1700
Data Index: 3749678 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.3447. Min Act: -0.1700
Data Index: 6022184 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.3447. Min Act: -0.1700
Data Index: 4961709 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.3290. Min Act: -0.1700
Data Index: 7425540 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.3290. Min Act: -0.1700
Data Index: 2541069 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.3290. Min Act: -0.1700
Data Index: 8458997 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2976. Min Act: -0.1700
Data Index: 7409209 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2976. Min Act: -0.1700
Data Index: 3668813 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2976. Min Act: -0.1700
Data Index: 440321 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2662. Min Act: -0.1700
Data Index: 7397548 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2976. Min Act: -0.1700
Data Index: 8145251 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2976. Min Act: -0.1700
Data Index: 3502286 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2976. Min Act: -0.1700
Data Index: 5809536 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2662. Min Act: -0.1700
Data Index: 3396566 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.3290. Min Act: -0.1700
Data Index: 8182481 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2505. Min Act: -0.1700
Data Index: 7194597 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2505. Min Act: -0.1700
Data Index: 4528704 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2662. Min Act: -0.1700
Data Index: 8343412 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4544. Min Range: -3.4544
Max Act: 3.2505. Min Act: -0.1700
Data Index: 986835 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19