Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4550 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.2667. Min Act: -0.1700
Data Index: 6002362 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.2042. Min Act: -0.1699
Data Index: 8368668 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.1730. Min Act: -0.1700
Data Index: 4131621 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.1417. Min Act: -0.1700
Data Index: 6002364 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.0792. Min Act: -0.1700
Data Index: 1874576 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.1105. Min Act: -0.1700
Data Index: 5155438 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.0792. Min Act: -0.1700
Data Index: 4726901 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.0792. Min Act: -0.1700
Data Index: 2305621 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.0480. Min Act: -0.1700
Data Index: 1430245 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.0167. Min Act: -0.1700
Data Index: 5860447 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.0167. Min Act: -0.1700
Data Index: 2919969 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2667. Min Range: -5.2667
Max Act: 4.9855. Min Act: -0.1700
Data Index: 3978092 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2667. Min Range: -5.2667
Max Act: 4.9542. Min Act: -0.1700
Data Index: 7722355 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2667. Min Range: -5.2667
Max Act: 4.9542. Min Act: -0.1700
Data Index: 3874857 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2667. Min Range: -5.2667
Max Act: 5.0167. Min Act: -0.1700
Data Index: 3857082 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2667. Min Range: -5.2667
Max Act: 4.9855. Min Act: -0.1700
Data Index: 4979900 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2667. Min Range: -5.2667
Max Act: 4.9855. Min Act: -0.1700
Data Index: 3567454 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2667. Min Range: -5.2667
Max Act: 4.9542. Min Act: -0.1700
Data Index: 915734 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2667. Min Range: -5.2667
Max Act: 4.9542. Min Act: -0.1700
Data Index: 2890284 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2667. Min Range: -5.2667
Max Act: 4.9542. Min Act: -0.1700
Data Index: 6026438 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19