Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0307. Min Range: -9.0307
Max Act: 9.0307. Min Act: -0.1700
Data Index: 709010 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.9682. Min Act: -0.1700
Data Index: 8780696 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.8432. Min Act: -0.1700
Data Index: 7278174 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.7807. Min Act: -0.1700
Data Index: 2546162 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.7807. Min Act: -0.1700
Data Index: 5517978 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.7807. Min Act: -0.1700
Data Index: 6933497 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.7182. Min Act: -0.1700
Data Index: 2872898 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5932. Min Act: -0.1700
Data Index: 6625890 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5932. Min Act: -0.1700
Data Index: 6700849 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5932. Min Act: -0.1700
Data Index: 2802543 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5932. Min Act: -0.1700
Data Index: 6299581 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 1950465 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 1220975 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 8392725 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 777947 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 2672915 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 5737396 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 3545713 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.5307. Min Act: -0.1700
Data Index: 5926734 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0307. Min Range: -9.0307
Max Act: 8.4682. Min Act: -0.1700
Data Index: 1301847 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19