Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5390 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.3108. Min Act: -0.1700
Data Index: 5744457 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3108. Min Range: -5.3108
Max Act: 5.0295. Min Act: -0.1700
Data Index: 2941801 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.9670. Min Act: -0.1700
Data Index: 3367574 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.9358. Min Act: -0.1700
Data Index: 2269073 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.9045. Min Act: -0.1700
Data Index: 8339557 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.9045. Min Act: -0.1700
Data Index: 1026793 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.9045. Min Act: -0.1700
Data Index: 3367573 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.8420. Min Act: -0.1700
Data Index: 3450374 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.8108. Min Act: -0.1700
Data Index: 8649335 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.8420. Min Act: -0.1700
Data Index: 5440954 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.7795. Min Act: -0.1700
Data Index: 2435338 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.8108. Min Act: -0.1700
Data Index: 8303286 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.7795. Min Act: -0.1700
Data Index: 4736746 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.8108. Min Act: -0.1700
Data Index: 6666106 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.8108. Min Act: -0.1700
Data Index: 3729286 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.7795. Min Act: -0.1700
Data Index: 5685623 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.7483. Min Act: -0.1700
Data Index: 2545256 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.7795. Min Act: -0.1700
Data Index: 2812113 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.7795. Min Act: -0.1700
Data Index: 6666105 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3108. Min Range: -5.3108
Max Act: 4.7795. Min Act: -0.1700
Data Index: 6084148 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19