Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4251 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2175. Min Range: -6.2175
Max Act: 6.2175. Min Act: -0.1700
Data Index: 7796998 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2175. Min Range: -6.2175
Max Act: 6.0925. Min Act: -0.1700
Data Index: 6820628 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2175. Min Range: -6.2175
Max Act: 6.0925. Min Act: -0.1700
Data Index: 2592464 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2175. Min Range: -6.2175
Max Act: 6.0300. Min Act: -0.1700
Data Index: 4527038 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2175. Min Range: -6.2175
Max Act: 6.0612. Min Act: -0.1700
Data Index: 7350751 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.9675. Min Act: -0.1700
Data Index: 8148146 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.9675. Min Act: -0.1700
Data Index: 8450811 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.9050. Min Act: -0.1700
Data Index: 1432737 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.8737. Min Act: -0.1700
Data Index: 7856180 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.8425. Min Act: -0.1700
Data Index: 4824197 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.8737. Min Act: -0.1700
Data Index: 2356675 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.8112. Min Act: -0.1700
Data Index: 7201598 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.8112. Min Act: -0.1700
Data Index: 2898689 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.8112. Min Act: -0.1700
Data Index: 2733855 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.7800. Min Act: -0.1700
Data Index: 5083117 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.7800. Min Act: -0.1700
Data Index: 307056 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.7487. Min Act: -0.1700
Data Index: 3113442 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.7175. Min Act: -0.1700
Data Index: 1960157 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.7487. Min Act: -0.1700
Data Index: 15373 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2175. Min Range: -6.2175
Max Act: 5.7487. Min Act: -0.1700
Data Index: 3593250 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19