Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.6781. Min Act: -0.1700
Data Index: 981890 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.5372. Min Act: -0.1700
Data Index: 981869 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.4903. Min Act: -0.1700
Data Index: 6059013 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.4276. Min Act: -0.1700
Data Index: 6603205 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.4119. Min Act: -0.1700
Data Index: 6965090 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3962. Min Act: -0.1700
Data Index: 4956958 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.4119. Min Act: -0.1700
Data Index: 2939919 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3649. Min Act: -0.1700
Data Index: 2403826 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3806. Min Act: -0.1700
Data Index: 7481553 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3492. Min Act: -0.1700
Data Index: 670578 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3492. Min Act: -0.1700
Data Index: 5050634 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3492. Min Act: -0.1700
Data Index: 981878 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3492. Min Act: -0.1700
Data Index: 487821 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3492. Min Act: -0.1700
Data Index: 8083120 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3021. Min Act: -0.1700
Data Index: 2682074 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3021. Min Act: -0.1700
Data Index: 752510 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3178. Min Act: -0.1700
Data Index: 744067 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.2707. Min Act: -0.1700
Data Index: 1542445 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.2864. Min Act: -0.1700
Data Index: 3918515 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6781. Min Range: -3.6781
Max Act: 3.3021. Min Act: -0.1700
Data Index: 3962361 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19