Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0526. Min Range: -7.0526
Max Act: 7.0526. Min Act: -0.1700
Data Index: 5668411 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.7714. Min Act: -0.1700
Data Index: 8095439 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.6464. Min Act: -0.1700
Data Index: 5456755 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.5839. Min Act: -0.1700
Data Index: 2013721 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.5214. Min Act: -0.1700
Data Index: 476350 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.4901. Min Act: -0.1700
Data Index: 4105201 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.5214. Min Act: -0.1700
Data Index: 2887517 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.4589. Min Act: -0.1700
Data Index: 140421 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.4901. Min Act: -0.1700
Data Index: 3891517 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.4589. Min Act: -0.1700
Data Index: 496303 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.4276. Min Act: -0.1700
Data Index: 5582407 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.4276. Min Act: -0.1700
Data Index: 2047205 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.4276. Min Act: -0.1700
Data Index: 7953229 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.3964. Min Act: -0.1700
Data Index: 7215449 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.3651. Min Act: -0.1700
Data Index: 8586868 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.3651. Min Act: -0.1700
Data Index: 8586870 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.3651. Min Act: -0.1700
Data Index: 6713194 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.3339. Min Act: -0.1700
Data Index: 5027307 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.3026. Min Act: -0.1700
Data Index: 8254242 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0526. Min Range: -7.0526
Max Act: 6.2714. Min Act: -0.1700
Data Index: 1260639 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19