Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 325 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.3044. Min Act: -0.1700
Data Index: 5977906 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.2731. Min Act: -0.1700
Data Index: 7300591 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.2731. Min Act: -0.1700
Data Index: 7668124 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.2731. Min Act: -0.1700
Data Index: 4754634 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.2419. Min Act: -0.1700
Data Index: 5342021 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.2106. Min Act: -0.1700
Data Index: 5205449 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1794. Min Act: -0.1700
Data Index: 6749581 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1794. Min Act: -0.1700
Data Index: 5037512 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1481. Min Act: -0.1700
Data Index: 3115116 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1169. Min Act: -0.1700
Data Index: 4563561 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1481. Min Act: -0.1700
Data Index: 3181738 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1481. Min Act: -0.1700
Data Index: 1574958 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1169. Min Act: -0.1700
Data Index: 5880438 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1169. Min Act: -0.1700
Data Index: 8364552 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1169. Min Act: -0.1700
Data Index: 4600919 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1169. Min Act: -0.1700
Data Index: 4059191 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.0856. Min Act: -0.1700
Data Index: 1743131 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.0856. Min Act: -0.1700
Data Index: 720616 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1169. Min Act: -0.1700
Data Index: 3700316 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.1169. Min Act: -0.1700
Data Index: 5314700 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19