Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2937. Min Act: -0.1700
Data Index: 3195804 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2937. Min Act: -0.1700
Data Index: 5232501 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2780. Min Act: -0.1700
Data Index: 7220063 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2623. Min Act: -0.1700
Data Index: 1262511 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2623. Min Act: -0.1700
Data Index: 2092282 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2623. Min Act: -0.1700
Data Index: 2368715 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2466. Min Act: -0.1700
Data Index: 2257104 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2309. Min Act: -0.1700
Data Index: 4939641 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2309. Min Act: -0.1700
Data Index: 6285437 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2151. Min Act: -0.1700
Data Index: 523140 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2151. Min Act: -0.1700
Data Index: 8210707 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2151. Min Act: -0.1700
Data Index: 7343712 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.2151. Min Act: -0.1700
Data Index: 35991 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.1994. Min Act: -0.1700
Data Index: 5826688 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.1994. Min Act: -0.1700
Data Index: 7108 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.1994. Min Act: -0.1700
Data Index: 2476970 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.1837. Min Act: -0.1700
Data Index: 3823230 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.1837. Min Act: -0.1700
Data Index: 5781294 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.1837. Min Act: -0.1700
Data Index: 3809120 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2937. Min Range: -3.2937
Max Act: 3.1837. Min Act: -0.1700
Data Index: 5204303 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19