Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2547. Min Range: -5.2547
Max Act: 5.2547. Min Act: -0.1700
Data Index: 4710402 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2547. Min Range: -5.2547
Max Act: 5.0047. Min Act: -0.1700
Data Index: 7386192 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.9734. Min Act: -0.1700
Data Index: 3132845 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.9422. Min Act: -0.1700
Data Index: 8751835 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.9422. Min Act: -0.1700
Data Index: 7618286 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.9422. Min Act: -0.1700
Data Index: 5311249 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.9422. Min Act: -0.1700
Data Index: 2535048 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.8484. Min Act: -0.1700
Data Index: 3138231 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.8484. Min Act: -0.1696
Data Index: 8751834 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.8484. Min Act: -0.1700
Data Index: 7595114 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.8172. Min Act: -0.1700
Data Index: 2717160 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.8797. Min Act: -0.1700
Data Index: 2676755 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.8484. Min Act: -0.1700
Data Index: 8554253 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.8484. Min Act: -0.1700
Data Index: 2037731 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.8172. Min Act: -0.1700
Data Index: 4704213 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.7859. Min Act: -0.1700
Data Index: 7131427 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.7859. Min Act: -0.1700
Data Index: 3555788 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.7859. Min Act: -0.1700
Data Index: 8428153 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.7859. Min Act: -0.1700
Data Index: 6541551 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2547. Min Range: -5.2547
Max Act: 4.7859. Min Act: -0.1700
Data Index: 3613037 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19