Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4827 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.9177. Min Act: -0.1700
Data Index: 5876838 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.4177. Min Act: -0.1700
Data Index: 3242271 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.3240. Min Act: -0.1700
Data Index: 2998685 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.2927. Min Act: -0.1700
Data Index: 1794560 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.2615. Min Act: -0.1700
Data Index: 7333241 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.2302. Min Act: -0.1700
Data Index: 5892632 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1990. Min Act: -0.1700
Data Index: 4049307 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1990. Min Act: -0.1700
Data Index: 4766354 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1677. Min Act: -0.1700
Data Index: 7318462 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1677. Min Act: -0.1700
Data Index: 5087649 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1677. Min Act: -0.1700
Data Index: 2243774 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1677. Min Act: -0.1700
Data Index: 4706666 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1677. Min Act: -0.1700
Data Index: 3186538 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1677. Min Act: -0.1700
Data Index: 1114180 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1365. Min Act: -0.1700
Data Index: 1568068 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1052. Min Act: -0.1700
Data Index: 1438379 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.1052. Min Act: -0.1700
Data Index: 2590391 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.0740. Min Act: -0.1700
Data Index: 4784164 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.0740. Min Act: -0.1700
Data Index: 2117606 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9177. Min Range: -5.9177
Max Act: 5.0740. Min Act: -0.1700
Data Index: 906631 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19