Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3084. Min Range: -4.3084
Max Act: 4.3084. Min Act: -0.1700
Data Index: 3313587 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3084. Min Range: -4.3084
Max Act: 4.0584. Min Act: -0.1700
Data Index: 8637159 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.9958. Min Act: -0.1700
Data Index: 4793567 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.9958. Min Act: -0.1700
Data Index: 250846 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.9646. Min Act: -0.1700
Data Index: 2317856 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.9646. Min Act: -0.1700
Data Index: 5632467 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.9646. Min Act: -0.1700
Data Index: 7851102 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.9333. Min Act: -0.1700
Data Index: 337918 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.9333. Min Act: -0.1700
Data Index: 8216500 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.8864. Min Act: -0.1700
Data Index: 6963138 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.9021. Min Act: -0.1700
Data Index: 1361596 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.8708. Min Act: -0.1700
Data Index: 6177386 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.8552. Min Act: -0.1700
Data Index: 8322949 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.8552. Min Act: -0.1700
Data Index: 4942325 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.8395. Min Act: -0.1700
Data Index: 5894075 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.8083. Min Act: -0.1700
Data Index: 3861063 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.8083. Min Act: -0.1700
Data Index: 6709274 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.7926. Min Act: -0.1700
Data Index: 7668120 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.7926. Min Act: -0.1700
Data Index: 4042193 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3084. Min Range: -4.3084
Max Act: 3.7926. Min Act: -0.1700
Data Index: 4118944 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19