Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4302 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3418. Min Range: -6.3418
Max Act: 6.3418. Min Act: -0.1700
Data Index: 7467703 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3418. Min Range: -6.3418
Max Act: 6.2168. Min Act: -0.1700
Data Index: 5523527 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3418. Min Range: -6.3418
Max Act: 6.0293. Min Act: -0.1700
Data Index: 3791758 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.8730. Min Act: -0.1700
Data Index: 594293 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.8730. Min Act: -0.1700
Data Index: 8340156 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.8730. Min Act: -0.1700
Data Index: 269843 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.8418. Min Act: -0.1700
Data Index: 8087884 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.8418. Min Act: -0.1700
Data Index: 6907578 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7793. Min Act: -0.1700
Data Index: 6518580 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7793. Min Act: -0.1700
Data Index: 6754663 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.8105. Min Act: -0.1700
Data Index: 6885954 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7793. Min Act: -0.1700
Data Index: 8218008 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7480. Min Act: -0.1700
Data Index: 7485990 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7793. Min Act: -0.1700
Data Index: 5579813 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7480. Min Act: -0.1700
Data Index: 7999022 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7480. Min Act: -0.1700
Data Index: 5465654 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7168. Min Act: -0.1700
Data Index: 2020947 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.7168. Min Act: -0.1700
Data Index: 5212472 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.6855. Min Act: -0.1700
Data Index: 2667290 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3418. Min Range: -6.3418
Max Act: 5.6543. Min Act: -0.1700
Data Index: 3727477 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19