Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.8121. Min Act: -0.1700
Data Index: 2191812 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.7183. Min Act: -0.1700
Data Index: 3129258 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.7183. Min Act: -0.1700
Data Index: 3606218 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.7496. Min Act: -0.1700
Data Index: 7324151 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.7809. Min Act: -0.1700
Data Index: 265890 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.6557. Min Act: -0.1700
Data Index: 3278885 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.6557. Min Act: -0.1700
Data Index: 797405 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5931. Min Act: -0.1700
Data Index: 6927074 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5618. Min Act: -0.1700
Data Index: 1717031 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5618. Min Act: -0.1700
Data Index: 2133186 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5931. Min Act: -0.1700
Data Index: 1542754 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5149. Min Act: -0.1700
Data Index: 1207170 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5305. Min Act: -0.1700
Data Index: 2019373 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5305. Min Act: -0.1700
Data Index: 1184636 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5305. Min Act: -0.1700
Data Index: 8659111 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5305. Min Act: -0.1700
Data Index: 4321223 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5305. Min Act: -0.1700
Data Index: 1422044 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.4679. Min Act: -0.1700
Data Index: 6569715 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5149. Min Act: -0.1700
Data Index: 7769830 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8121. Min Range: -3.8121
Max Act: 3.5149. Min Act: -0.1700
Data Index: 2466155 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19