Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.8362. Min Act: -0.1700
Data Index: 4609815 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7423. Min Act: -0.1700
Data Index: 4099534 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7423. Min Act: -0.1700
Data Index: 3935112 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7423. Min Act: -0.1700
Data Index: 6634472 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7111. Min Act: -0.1700
Data Index: 842391 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7111. Min Act: -0.1700
Data Index: 7519976 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7111. Min Act: -0.1700
Data Index: 2209268 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.7111. Min Act: -0.1700
Data Index: 4202843 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6954. Min Act: -0.1700
Data Index: 855488 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6485. Min Act: -0.1700
Data Index: 7140376 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6641. Min Act: -0.1700
Data Index: 7421436 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6641. Min Act: -0.1700
Data Index: 8736526 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6798. Min Act: -0.1700
Data Index: 8148021 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6328. Min Act: -0.1700
Data Index: 7239799 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6485. Min Act: -0.1700
Data Index: 6755465 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6485. Min Act: -0.1700
Data Index: 1718146 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6328. Min Act: -0.1700
Data Index: 4557098 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6172. Min Act: -0.1700
Data Index: 3362460 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6172. Min Act: -0.1700
Data Index: 1822112 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8362. Min Range: -3.8362
Max Act: 3.6485. Min Act: -0.1700
Data Index: 1341106 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19