Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2840 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3747. Min Range: -6.3747
Max Act: 6.3747. Min Act: -0.1700
Data Index: 1392449 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3747. Min Range: -6.3747
Max Act: 6.0935. Min Act: -0.1700
Data Index: 8733398 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.9997. Min Act: -0.1700
Data Index: 8481844 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.9060. Min Act: -0.1700
Data Index: 5468838 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.9060. Min Act: -0.1700
Data Index: 849438 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.8747. Min Act: -0.1700
Data Index: 5191181 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.8747. Min Act: -0.1700
Data Index: 8337588 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.8122. Min Act: -0.1700
Data Index: 1943971 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.8122. Min Act: -0.1700
Data Index: 2845294 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.8122. Min Act: -0.1700
Data Index: 6089275 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.8122. Min Act: -0.1700
Data Index: 2490426 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.7810. Min Act: -0.1700
Data Index: 4123825 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 8770107 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 8481079 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 4707810 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 2552492 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 1967243 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.7497. Min Act: -0.1700
Data Index: 5694975 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.6872. Min Act: -0.1700
Data Index: 6874268 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3747. Min Range: -6.3747
Max Act: 5.7185. Min Act: -0.1700
Data Index: 6987551 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19