Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.5167. Min Act: -0.1700
Data Index: 1070724 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.4230. Min Act: -0.1700
Data Index: 6154811 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.3917. Min Act: -0.1700
Data Index: 3238565 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.3605. Min Act: -0.1700
Data Index: 1677923 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.3605. Min Act: -0.1700
Data Index: 3729243 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.2980. Min Act: -0.1700
Data Index: 4910408 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.2667. Min Act: -0.1700
Data Index: 323916 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.2042. Min Act: -0.1700
Data Index: 8137745 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.2042. Min Act: -0.1700
Data Index: 3537073 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.2042. Min Act: -0.1700
Data Index: 4076219 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.1417. Min Act: -0.1700
Data Index: 7469589 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.1730. Min Act: -0.1700
Data Index: 703904 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.1105. Min Act: -0.1700
Data Index: 7524748 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.0792. Min Act: -0.1700
Data Index: 2174753 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.0792. Min Act: -0.1700
Data Index: 3154885 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.0480. Min Act: -0.1700
Data Index: 8469487 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.0792. Min Act: -0.1700
Data Index: 1921603 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.0480. Min Act: -0.1700
Data Index: 699 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.0480. Min Act: -0.1700
Data Index: 4915487 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5167. Min Range: -7.5167
Max Act: 7.0480. Min Act: -0.1700
Data Index: 2013938 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19