Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0699. Min Range: -7.0699
Max Act: 7.0699. Min Act: -0.1700
Data Index: 6323024 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.9449. Min Act: -0.1700
Data Index: 3203726 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.8511. Min Act: -0.1700
Data Index: 6082094 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.7886. Min Act: -0.1700
Data Index: 2063194 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.7886. Min Act: -0.1700
Data Index: 7118738 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6949. Min Act: -0.1700
Data Index: 5385611 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6636. Min Act: -0.1700
Data Index: 2879987 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6949. Min Act: -0.1700
Data Index: 47496 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6636. Min Act: -0.1700
Data Index: 3580412 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6636. Min Act: -0.1700
Data Index: 666808 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6636. Min Act: -0.1700
Data Index: 8550338 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6324. Min Act: -0.1700
Data Index: 792241 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6324. Min Act: -0.1700
Data Index: 8830700 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.6011. Min Act: -0.1700
Data Index: 6722010 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.5699. Min Act: -0.1700
Data Index: 7884321 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.5699. Min Act: -0.1700
Data Index: 3227843 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.5386. Min Act: -0.1700
Data Index: 5177471 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.5386. Min Act: -0.1700
Data Index: 111950 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.4761. Min Act: -0.1700
Data Index: 2719942 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0699. Min Range: -7.0699
Max Act: 6.4761. Min Act: -0.1700
Data Index: 5077452 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19