Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.2304. Min Act: -0.1700
Data Index: 4321517 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.2304. Min Act: -0.1700
Data Index: 6812611 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1992. Min Act: -0.1700
Data Index: 4529265 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1366. Min Act: -0.1700
Data Index: 7346940 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1366. Min Act: -0.1700
Data Index: 940611 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1366. Min Act: -0.1700
Data Index: 5000801 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1366. Min Act: -0.1700
Data Index: 3557394 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1679. Min Act: -0.1700
Data Index: 4514427 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1366. Min Act: -0.1700
Data Index: 4131864 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1054. Min Act: -0.1700
Data Index: 347814 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1054. Min Act: -0.1700
Data Index: 6329778 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1366. Min Act: -0.1700
Data Index: 1980870 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1054. Min Act: -0.1700
Data Index: 2700626 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.1054. Min Act: -0.1700
Data Index: 7505814 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0741. Min Act: -0.1700
Data Index: 2020819 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0429. Min Act: -0.1700
Data Index: 6571187 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0429. Min Act: -0.1700
Data Index: 4900944 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0116. Min Act: -0.1700
Data Index: 3480145 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0429. Min Act: -0.1700
Data Index: 207963 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2304. Min Range: -4.2304
Max Act: 4.0429. Min Act: -0.1700
Data Index: 6329782 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19