Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1143. Min Range: -7.1143
Max Act: 7.1143. Min Act: -0.1700
Data Index: 5722912 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.7706. Min Act: -0.1700
Data Index: 7295759 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.7393. Min Act: -0.1700
Data Index: 1083888 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.6768. Min Act: -0.1700
Data Index: 3296634 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.5206. Min Act: -0.1700
Data Index: 2625131 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.4893. Min Act: -0.1700
Data Index: 4020347 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.4268. Min Act: -0.1700
Data Index: 3569590 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.3643. Min Act: -0.1700
Data Index: 3040617 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.3018. Min Act: -0.1700
Data Index: 1685387 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.2706. Min Act: -0.1700
Data Index: 1691095 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.2393. Min Act: -0.1700
Data Index: 2219906 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.2081. Min Act: -0.1700
Data Index: 7331408 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.2081. Min Act: -0.1700
Data Index: 8062159 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.1768. Min Act: -0.1700
Data Index: 8642868 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.1768. Min Act: -0.1700
Data Index: 3939090 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.1768. Min Act: -0.1700
Data Index: 340968 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.1456. Min Act: -0.1700
Data Index: 2261929 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.1143. Min Act: -0.1700
Data Index: 3647305 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.1143. Min Act: -0.1700
Data Index: 7864895 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1143. Min Range: -7.1143
Max Act: 6.1143. Min Act: -0.1700
Data Index: 3475146 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19