Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0152. Min Range: -6.0152
Max Act: 6.0152. Min Act: -0.1700
Data Index: 8525673 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0152. Min Range: -6.0152
Max Act: 6.0152. Min Act: -0.1700
Data Index: 7003685 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.9840. Min Act: -0.1700
Data Index: 4760812 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.9840. Min Act: -0.1700
Data Index: 5334035 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.9527. Min Act: -0.1700
Data Index: 8600045 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.9527. Min Act: -0.1700
Data Index: 6184745 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.9527. Min Act: -0.1700
Data Index: 8395974 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.9527. Min Act: -0.1700
Data Index: 7659096 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.9215. Min Act: -0.1700
Data Index: 2584738 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 3033968 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 3033971 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8590. Min Act: -0.1700
Data Index: 3033972 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 7029347 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 12470 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 1932040 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 4760802 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 2104828 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 6234728 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 298991 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0152. Min Range: -6.0152
Max Act: 5.8590. Min Act: -0.1700
Data Index: 3513638 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19