Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2999 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.5110. Min Act: -0.1700
Data Index: 2172513 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.4172. Min Act: -0.1700
Data Index: 5363710 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.3860. Min Act: -0.1700
Data Index: 5785818 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.3547. Min Act: -0.1700
Data Index: 5122431 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.3547. Min Act: -0.1700
Data Index: 4970811 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.3547. Min Act: -0.1700
Data Index: 5402940 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2922. Min Act: -0.1700
Data Index: 7997520 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2922. Min Act: -0.1700
Data Index: 4338703 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2922. Min Act: -0.1700
Data Index: 5907262 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2922. Min Act: -0.1700
Data Index: 8269896 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2922. Min Act: -0.1700
Data Index: 1741625 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2922. Min Act: -0.1700
Data Index: 5199168 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2922. Min Act: -0.1700
Data Index: 1050360 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2610. Min Act: -0.1700
Data Index: 5808660 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2610. Min Act: -0.1700
Data Index: 5350653 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.2297. Min Act: -0.1700
Data Index: 41116 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.1985. Min Act: -0.1700
Data Index: 82488 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.1985. Min Act: -0.1700
Data Index: 4772168 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.1672. Min Act: -0.1700
Data Index: 5624012 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5110. Min Range: -5.5110
Max Act: 5.1672. Min Act: -0.1700
Data Index: 7108592 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19