Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.0697. Min Range: -4.0697
Max Act: 4.0697. Min Act: -0.1700
Data Index: 2361400 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.8508. Min Act: -0.1700
Data Index: 5351619 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.7883. Min Act: -0.1700
Data Index: 3133213 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.7883. Min Act: -0.1700
Data Index: 7906415 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.7570. Min Act: -0.1700
Data Index: 5168035 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6944. Min Act: -0.1700
Data Index: 4239246 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.7257. Min Act: -0.1700
Data Index: 8136321 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.7257. Min Act: -0.1700
Data Index: 6634503 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.7257. Min Act: -0.1700
Data Index: 6635479 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6944. Min Act: -0.1700
Data Index: 4387611 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6944. Min Act: -0.1700
Data Index: 6885392 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6944. Min Act: -0.1700
Data Index: 4273676 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6944. Min Act: -0.1700
Data Index: 5580273 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6631. Min Act: -0.1700
Data Index: 6844071 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6318. Min Act: -0.1700
Data Index: 4965595 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6631. Min Act: -0.1700
Data Index: 1828666 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6631. Min Act: -0.1700
Data Index: 6103177 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6944. Min Act: -0.1700
Data Index: 816789 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6631. Min Act: -0.1700
Data Index: 8580000 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0697. Min Range: -4.0697
Max Act: 3.6631. Min Act: -0.1700
Data Index: 8759226 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19