Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6964. Min Act: -0.1700
Data Index: 7916023 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.7277. Min Act: -0.1700
Data Index: 2231521 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.7433. Min Act: -0.1700
Data Index: 767952 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6651. Min Act: -0.1700
Data Index: 7138520 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6182. Min Act: -0.1700
Data Index: 867912 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6025. Min Act: -0.1700
Data Index: 5772915 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5869. Min Act: -0.1700
Data Index: 4400346 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5869. Min Act: -0.1700
Data Index: 8127140 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6025. Min Act: -0.1700
Data Index: 3890355 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.6025. Min Act: -0.1700
Data Index: 2176857 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5242. Min Act: -0.1700
Data Index: 728792 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5399. Min Act: -0.1700
Data Index: 1548619 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5556. Min Act: -0.1700
Data Index: 944941 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5399. Min Act: -0.1700
Data Index: 8255002 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5399. Min Act: -0.1700
Data Index: 6562280 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5242. Min Act: -0.1700
Data Index: 7879951 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5242. Min Act: -0.1700
Data Index: 2511115 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5242. Min Act: -0.1700
Data Index: 5253297 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5242. Min Act: -0.1700
Data Index: 4098386 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5399. Min Act: -0.1700
Data Index: 859859 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19