Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1084 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.3803. Min Act: -0.1700
Data Index: 7139953 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.2553. Min Act: -0.1700
Data Index: 2839652 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.2240. Min Act: -0.1700
Data Index: 3392851 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.1928. Min Act: -0.1700
Data Index: 7628692 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.1615. Min Act: -0.1700
Data Index: 6063816 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.1928. Min Act: -0.1700
Data Index: 2874337 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.1615. Min Act: -0.1700
Data Index: 7853997 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.1615. Min Act: -0.1700
Data Index: 8204962 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.1615. Min Act: -0.1700
Data Index: 3733930 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0990. Min Act: -0.1700
Data Index: 8730815 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0990. Min Act: -0.1700
Data Index: 6058236 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0990. Min Act: -0.1700
Data Index: 7255844 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0678. Min Act: -0.1700
Data Index: 2168648 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0365. Min Act: -0.1700
Data Index: 7660518 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0678. Min Act: -0.1700
Data Index: 8222099 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0678. Min Act: -0.1700
Data Index: 2235848 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0990. Min Act: -0.1700
Data Index: 662838 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0365. Min Act: -0.1700
Data Index: 5510090 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6329424 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3803. Min Range: -5.3803
Max Act: 5.0678. Min Act: -0.1700
Data Index: 5559888 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19