Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.6835. Min Act: -0.1700
Data Index: 5877222 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.6210. Min Act: -0.1700
Data Index: 8504580 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.6835. Min Act: -0.1700
Data Index: 3728804 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.6210. Min Act: -0.1700
Data Index: 498664 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.6835. Min Act: -0.1700
Data Index: 7100839 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.6210. Min Act: -0.1700
Data Index: 7244304 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.4960. Min Act: -0.1700
Data Index: 7675089 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.4960. Min Act: -0.1700
Data Index: 7958662 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.5273. Min Act: -0.1700
Data Index: 1870214 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.4335. Min Act: -0.1700
Data Index: 5914532 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.4335. Min Act: -0.1700
Data Index: 4902554 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.4335. Min Act: -0.1700
Data Index: 5822757 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.4023. Min Act: -0.1700
Data Index: 1282121 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.3085. Min Act: -0.1700
Data Index: 1080721 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.4335. Min Act: -0.1700
Data Index: 2501031 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.3085. Min Act: -0.1700
Data Index: 7951534 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.3398. Min Act: -0.1700
Data Index: 8425284 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.3085. Min Act: -0.1700
Data Index: 5853206 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.3085. Min Act: -0.1700
Data Index: 4846629 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6835. Min Range: -7.6835
Max Act: 7.3085. Min Act: -0.1700
Data Index: 3524056 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19