Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 892 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.4453. Min Act: -0.1700
Data Index: 6979503 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.3042. Min Act: -0.1700
Data Index: 5108315 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.2885. Min Act: -0.1700
Data Index: 3276785 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.1155. Min Act: -0.1700
Data Index: 4357895 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0997. Min Act: -0.1700
Data Index: 3615610 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0997. Min Act: -0.1700
Data Index: 888128 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0840. Min Act: -0.1700
Data Index: 3891886 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0840. Min Act: -0.1700
Data Index: 1805300 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0682. Min Act: -0.1700
Data Index: 6298384 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0682. Min Act: -0.1700
Data Index: 888129 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0682. Min Act: -0.1700
Data Index: 4803744 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0682. Min Act: -0.1700
Data Index: 2235259 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0051. Min Act: -0.1700
Data Index: 1444843 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0051. Min Act: -0.1700
Data Index: 2884125 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0209. Min Act: -0.1700
Data Index: 4900942 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4453. Min Range: -3.4453
Max Act: 3.0209. Min Act: -0.1700
Data Index: 7354500 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4453. Min Range: -3.4453
Max Act: 2.9893. Min Act: -0.1700
Data Index: 2978100 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4453. Min Range: -3.4453
Max Act: 2.9734. Min Act: -0.1700
Data Index: 2058101 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4453. Min Range: -3.4453
Max Act: 2.9893. Min Act: -0.1700
Data Index: 6094858 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4453. Min Range: -3.4453
Max Act: 2.9734. Min Act: -0.1700
Data Index: 4292508 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19