Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0897. Min Range: -2.0897
Max Act: 2.0897. Min Act: -0.1700
Data Index: 8805191 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.9886. Min Act: -0.1700
Data Index: 1272275 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0897. Min Range: -2.0897
Max Act: 2.0055. Min Act: -0.1700
Data Index: 5695604 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.9547. Min Act: -0.1700
Data Index: 5894417 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.9547. Min Act: -0.1700
Data Index: 3497533 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.9378. Min Act: -0.1700
Data Index: 2032889 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8952. Min Act: -0.1700
Data Index: 3685639 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8952. Min Act: -0.1700
Data Index: 7714623 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.9207. Min Act: -0.1700
Data Index: 2972923 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.9037. Min Act: -0.1700
Data Index: 8668776 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8952. Min Act: -0.1700
Data Index: 8519525 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8867. Min Act: -0.1700
Data Index: 7709158 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8952. Min Act: -0.1700
Data Index: 5657650 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8781. Min Act: -0.1700
Data Index: 3662238 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8524. Min Act: -0.1700
Data Index: 3140440 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8610. Min Act: -0.1700
Data Index: 6516701 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8524. Min Act: -0.1700
Data Index: 8622724 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8524. Min Act: -0.1700
Data Index: 3099669 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8439. Min Act: -0.1700
Data Index: 635831 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0897. Min Range: -2.0897
Max Act: 1.8524. Min Act: -0.1700
Data Index: 6832578 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19