Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3894 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.9460. Min Act: -0.1700
Data Index: 719191 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.7585. Min Act: -0.1700
Data Index: 1598335 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.5085. Min Act: -0.1700
Data Index: 2133352 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.5085. Min Act: -0.1700
Data Index: 1152320 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.4460. Min Act: -0.1700
Data Index: 1753193 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.4460. Min Act: -0.1700
Data Index: 8232464 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.3835. Min Act: -0.1700
Data Index: 5096063 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.4460. Min Act: -0.1700
Data Index: 7569748 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.3835. Min Act: -0.1700
Data Index: 5076821 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.3835. Min Act: -0.1700
Data Index: 4867043 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.2585. Min Act: -0.1700
Data Index: 8127998 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.1960. Min Act: -0.1700
Data Index: 1586854 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.2585. Min Act: -0.1700
Data Index: 2467424 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.2585. Min Act: -0.1700
Data Index: 5107946 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.2585. Min Act: -0.1700
Data Index: 5422282 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.2585. Min Act: -0.1700
Data Index: 6250762 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.1960. Min Act: -0.1700
Data Index: 101529 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.1335. Min Act: -0.1700
Data Index: 2162623 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.1960. Min Act: -0.1700
Data Index: 4392772 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9460. Min Range: -8.9460
Max Act: 8.1960. Min Act: -0.1700
Data Index: 6851140 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19