Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.7703. Min Act: -0.1700
Data Index: 4938707 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.5203. Min Act: -0.1700
Data Index: 4367942 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.4578. Min Act: -0.1700
Data Index: 8278740 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.3953. Min Act: -0.1700
Data Index: 7687437 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.2703. Min Act: -0.1700
Data Index: 8292632 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.2703. Min Act: -0.1700
Data Index: 7641 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.1453. Min Act: -0.1700
Data Index: 4337505 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.1453. Min Act: -0.1700
Data Index: 4542897 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.1453. Min Act: -0.1700
Data Index: 3357936 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7703. Min Range: -8.7703
Max Act: 8.0828. Min Act: -0.1700
Data Index: 7791991 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.8953. Min Act: -0.1700
Data Index: 2503278 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.7703. Min Act: -0.1700
Data Index: 8173066 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.8953. Min Act: -0.1700
Data Index: 7430044 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.7703. Min Act: -0.1700
Data Index: 6621773 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.7078. Min Act: -0.1700
Data Index: 5317819 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.7703. Min Act: -0.1700
Data Index: 5136486 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.7078. Min Act: -0.1700
Data Index: 6367948 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.6453. Min Act: -0.1700
Data Index: 6715144 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.6453. Min Act: -0.1700
Data Index: 1530568 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7703. Min Range: -8.7703
Max Act: 7.5828. Min Act: -0.1700
Data Index: 6774258 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19