Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6021 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.8526. Min Act: -0.1700
Data Index: 6624834 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.6651. Min Act: -0.1700
Data Index: 8489181 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.5401. Min Act: -0.1700
Data Index: 8666532 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.5401. Min Act: -0.1700
Data Index: 251043 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.4776. Min Act: -0.1700
Data Index: 4696116 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.4151. Min Act: -0.1700
Data Index: 6218145 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.4151. Min Act: -0.1700
Data Index: 6354669 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.3526. Min Act: -0.1700
Data Index: 7938056 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.3526. Min Act: -0.1700
Data Index: 5983304 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.2276. Min Act: -0.1700
Data Index: 1405271 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.2276. Min Act: -0.1700
Data Index: 1605571 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.1651. Min Act: -0.1700
Data Index: 5428788 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.2276. Min Act: -0.1700
Data Index: 6005330 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.1651. Min Act: -0.1700
Data Index: 8539378 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.1026. Min Act: -0.1700
Data Index: 315183 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.1026. Min Act: -0.1700
Data Index: 7663027 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.1651. Min Act: -0.1700
Data Index: 1410985 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.1026. Min Act: -0.1700
Data Index: 8319615 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.1026. Min Act: -0.1700
Data Index: 5833856 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8526. Min Range: -8.8526
Max Act: 8.0401. Min Act: -0.1700
Data Index: 5185473 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19