Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.9214. Min Act: -0.1700
Data Index: 5483181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8902. Min Act: -0.1700
Data Index: 2395953 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8902. Min Act: -0.1700
Data Index: 4602642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8902. Min Act: -0.1700
Data Index: 4526843 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8902. Min Act: -0.1700
Data Index: 4064150 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8902. Min Act: -0.1700
Data Index: 8277735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8902. Min Act: -0.1700
Data Index: 7924618 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8902. Min Act: -0.1700
Data Index: 2554789 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8902. Min Act: -0.1700
Data Index: 5025845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 3215506 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 3234238 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 4296655 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 1541359 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 4820694 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 4830568 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 4920625 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 2004710 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 4952765 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 2070246 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9214. Min Range: -3.9214
Max Act: 3.8589. Min Act: -0.1700
Data Index: 490744 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19