Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0393. Min Range: -8.0393
Max Act: 8.0393. Min Act: -0.1700
Data Index: 3239727 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.7268. Min Act: -0.1700
Data Index: 5236615 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.7268. Min Act: -0.1700
Data Index: 3523336 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.6643. Min Act: -0.1700
Data Index: 4487395 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.4456. Min Act: -0.1700
Data Index: 4744222 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.4143. Min Act: -0.1700
Data Index: 7767548 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.3206. Min Act: -0.1700
Data Index: 6326519 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.2893. Min Act: -0.1700
Data Index: 1236473 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.2581. Min Act: -0.1700
Data Index: 8074257 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.2581. Min Act: -0.1700
Data Index: 3508805 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.2268. Min Act: -0.1700
Data Index: 565384 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.2581. Min Act: -0.1700
Data Index: 3547209 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.2268. Min Act: -0.1700
Data Index: 610390 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.1956. Min Act: -0.1700
Data Index: 1772834 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.1643. Min Act: -0.1700
Data Index: 971527 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.1643. Min Act: -0.1700
Data Index: 8729603 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.1643. Min Act: -0.1700
Data Index: 7741204 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.1331. Min Act: -0.1700
Data Index: 270938 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.1331. Min Act: -0.1700
Data Index: 8742838 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0393. Min Range: -8.0393
Max Act: 7.0706. Min Act: -0.1700
Data Index: 4347893 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19