Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1511 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.4044. Min Act: -0.1700
Data Index: 618110 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.2003. Min Act: -0.1700
Data Index: 2103247 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.1374. Min Act: -0.1700
Data Index: 7096154 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.1374. Min Act: -0.1700
Data Index: 4984157 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.1374. Min Act: -0.1700
Data Index: 8719931 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0901. Min Act: -0.1700
Data Index: 4032309 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0270. Min Act: -0.1700
Data Index: 2923179 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0428. Min Act: -0.1700
Data Index: 370552 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0428. Min Act: -0.1700
Data Index: 5478283 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0112. Min Act: -0.1700
Data Index: 748647 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4044. Min Range: -3.4044
Max Act: 2.9954. Min Act: -0.1700
Data Index: 986672 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0112. Min Act: -0.1700
Data Index: 6982517 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0112. Min Act: -0.1700
Data Index: 159881 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0112. Min Act: -0.1700
Data Index: 5653104 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4044. Min Range: -3.4044
Max Act: 3.0112. Min Act: -0.1700
Data Index: 1271652 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4044. Min Range: -3.4044
Max Act: 2.9954. Min Act: -0.1700
Data Index: 3010486 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4044. Min Range: -3.4044
Max Act: 2.9954. Min Act: -0.1700
Data Index: 2469633 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4044. Min Range: -3.4044
Max Act: 2.9954. Min Act: -0.1700
Data Index: 6224337 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4044. Min Range: -3.4044
Max Act: 2.9954. Min Act: -0.1700
Data Index: 7618786 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4044. Min Range: -3.4044
Max Act: 2.9954. Min Act: -0.1700
Data Index: 7149625 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19