Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1618 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0867. Min Range: -7.0867
Max Act: 7.0867. Min Act: -0.1700
Data Index: 6845573 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0867. Min Range: -7.0867
Max Act: 7.0554. Min Act: -0.1700
Data Index: 3171193 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.8367. Min Act: -0.1700
Data Index: 7453985 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.8367. Min Act: -0.1700
Data Index: 5545224 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.6492. Min Act: -0.1700
Data Index: 6518053 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.6179. Min Act: -0.1700
Data Index: 3630377 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.5242. Min Act: -0.1700
Data Index: 927732 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.4617. Min Act: -0.1700
Data Index: 4265773 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.4617. Min Act: -0.1700
Data Index: 2321044 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3992. Min Act: -0.1700
Data Index: 3130997 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3679. Min Act: -0.1700
Data Index: 1182465 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3679. Min Act: -0.1700
Data Index: 7633972 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3679. Min Act: -0.1700
Data Index: 2491692 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3367. Min Act: -0.1700
Data Index: 7030326 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3367. Min Act: -0.1700
Data Index: 1048747 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3054. Min Act: -0.1700
Data Index: 785086 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3054. Min Act: -0.1700
Data Index: 7003177 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.2429. Min Act: -0.1700
Data Index: 4356359 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.3054. Min Act: -0.1700
Data Index: 2470945 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0867. Min Range: -7.0867
Max Act: 6.2429. Min Act: -0.1700
Data Index: 647984 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19