Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0547. Min Range: -9.0547
Max Act: 9.0547. Min Act: -0.1700
Data Index: 4763254 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.9922. Min Act: -0.1700
Data Index: 2548383 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.8672. Min Act: -0.1700
Data Index: 2473570 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.8672. Min Act: -0.1700
Data Index: 2864168 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.8047. Min Act: -0.1700
Data Index: 6926211 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.8047. Min Act: -0.1700
Data Index: 4970798 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.8047. Min Act: -0.1700
Data Index: 1456201 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.7422. Min Act: -0.1700
Data Index: 1945195 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.7422. Min Act: -0.1700
Data Index: 3961980 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.7422. Min Act: -0.1700
Data Index: 6508343 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.7422. Min Act: -0.1700
Data Index: 8000103 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.7422. Min Act: -0.1700
Data Index: 612886 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.7422. Min Act: -0.1700
Data Index: 769012 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.6797. Min Act: -0.1700
Data Index: 5594175 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.7422. Min Act: -0.1700
Data Index: 115045 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.6797. Min Act: -0.1700
Data Index: 3095707 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.6172. Min Act: -0.1700
Data Index: 6175949 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.6172. Min Act: -0.1700
Data Index: 6246399 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.6172. Min Act: -0.1700
Data Index: 860142 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0547. Min Range: -9.0547
Max Act: 8.6172. Min Act: -0.1700
Data Index: 975101 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19