Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.5726. Min Act: -0.1700
Data Index: 7567093 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.5564. Min Act: -0.1700
Data Index: 4564813 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.5403. Min Act: -0.1700
Data Index: 1017506 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.5241. Min Act: -0.1700
Data Index: 3841122 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.5079. Min Act: -0.1700
Data Index: 3832180 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.5079. Min Act: -0.1700
Data Index: 1964974 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4755. Min Act: -0.1700
Data Index: 5411936 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4755. Min Act: -0.1700
Data Index: 1028256 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4593. Min Act: -0.1700
Data Index: 6794030 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4593. Min Act: -0.1700
Data Index: 8799120 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4593. Min Act: -0.1700
Data Index: 535635 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4593. Min Act: -0.1700
Data Index: 1296233 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4593. Min Act: -0.1700
Data Index: 455091 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4593. Min Act: -0.1700
Data Index: 3360366 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4593. Min Act: -0.1700
Data Index: 4477827 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4430. Min Act: -0.1700
Data Index: 4195729 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4267. Min Act: -0.1700
Data Index: 3035904 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4430. Min Act: -0.1700
Data Index: 4228605 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4430. Min Act: -0.1700
Data Index: 4540028 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5726. Min Range: -2.5726
Max Act: 2.4430. Min Act: -0.1700
Data Index: 2016958 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19