Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5058 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.4896. Min Act: -0.1700
Data Index: 6130124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.3646. Min Act: -0.1700
Data Index: 4067107 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.3333. Min Act: -0.1700
Data Index: 3855443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.3333. Min Act: -0.1700
Data Index: 3140851 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.3021. Min Act: -0.1700
Data Index: 4060285 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.3021. Min Act: -0.1693
Data Index: 4013224 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.3021. Min Act: -0.1700
Data Index: 1844984 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.3021. Min Act: -0.1700
Data Index: 3855437 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1700
Data Index: 5472957 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1700
Data Index: 5500860 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1698
Data Index: 5709326 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1700
Data Index: 5709325 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1700
Data Index: 1790484 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1630
Data Index: 4646450 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1700
Data Index: 6746390 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1700
Data Index: 2608378 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1635
Data Index: 7443386 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1700
Data Index: 7811615 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2708. Min Act: -0.1700
Data Index: 8339352 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4896. Min Range: -5.4896
Max Act: 5.2396. Min Act: -0.1700
Data Index: 863165 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19