Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5296. Min Range: -10.5296
Max Act: 10.5296. Min Act: -0.1700
Data Index: 3715660 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5296. Min Range: -10.5296
Max Act: 10.2171. Min Act: -0.1700
Data Index: 2655349 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.9671. Min Act: -0.1700
Data Index: 7083136 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.9671. Min Act: -0.1700
Data Index: 6143089 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.9046. Min Act: -0.1700
Data Index: 7902060 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.9046. Min Act: -0.1700
Data Index: 1221284 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.9046. Min Act: -0.1700
Data Index: 3715677 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.7171. Min Act: -0.1700
Data Index: 3681542 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.7171. Min Act: -0.1700
Data Index: 7793226 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.7171. Min Act: -0.1700
Data Index: 6020454 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.7171. Min Act: -0.1700
Data Index: 5697727 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.7171. Min Act: -0.1700
Data Index: 7083123 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.6546. Min Act: -0.1700
Data Index: 2570090 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.6546. Min Act: -0.1700
Data Index: 1524622 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.6546. Min Act: -0.1700
Data Index: 4350632 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.6546. Min Act: -0.1700
Data Index: 8285463 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.6546. Min Act: -0.1700
Data Index: 5314606 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.6546. Min Act: -0.1700
Data Index: 5098964 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.5921. Min Act: -0.1700
Data Index: 2443833 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5296. Min Range: -10.5296
Max Act: 9.5296. Min Act: -0.1700
Data Index: 7083137 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19