Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.5694. Min Act: -0.1700
Data Index: 5778141 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.6006. Min Act: -0.1700
Data Index: 7044093 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.4444. Min Act: -0.1700
Data Index: 4262002 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.3819. Min Act: -0.1700
Data Index: 6143321 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.4444. Min Act: -0.1700
Data Index: 8408933 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.3506. Min Act: -0.1700
Data Index: 4602235 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.3506. Min Act: -0.1700
Data Index: 6775593 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.3194. Min Act: -0.1700
Data Index: 1905908 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2881. Min Act: -0.1700
Data Index: 7109198 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.3194. Min Act: -0.1700
Data Index: 5229813 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2569. Min Act: -0.1700
Data Index: 714239 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2256. Min Act: -0.1700
Data Index: 5128326 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2256. Min Act: -0.1700
Data Index: 987448 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2256. Min Act: -0.1700
Data Index: 8371493 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2569. Min Act: -0.1700
Data Index: 1578213 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.2256. Min Act: -0.1700
Data Index: 2249437 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1944. Min Act: -0.1700
Data Index: 388486 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1944. Min Act: -0.1700
Data Index: 1733058 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1944. Min Act: -0.1700
Data Index: 414140 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6006. Min Range: -5.6006
Max Act: 5.1944. Min Act: -0.1700
Data Index: 6414964 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19