Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6151 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.3806. Min Act: -0.1700
Data Index: 3730278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.4119. Min Act: -0.1700
Data Index: 4232462 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.3494. Min Act: -0.1700
Data Index: 764818 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.2869. Min Act: -0.1700
Data Index: 479126 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.2556. Min Act: -0.1700
Data Index: 7954081 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.2244. Min Act: -0.1700
Data Index: 4587441 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.1931. Min Act: -0.1700
Data Index: 5905246 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.2244. Min Act: -0.1700
Data Index: 2609124 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.1306. Min Act: -0.1700
Data Index: 833140 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.1931. Min Act: -0.1700
Data Index: 3777317 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.1306. Min Act: -0.1700
Data Index: 2895169 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.1306. Min Act: -0.1700
Data Index: 2808309 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.0681. Min Act: -0.1700
Data Index: 3250387 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.0368. Min Act: -0.1700
Data Index: 7260644 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.0368. Min Act: -0.1700
Data Index: 7992751 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.0368. Min Act: -0.1700
Data Index: 958021 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.0368. Min Act: -0.1700
Data Index: 4054580 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.0368. Min Act: -0.1700
Data Index: 5032468 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.0681. Min Act: -0.1700
Data Index: 3867676 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4119. Min Range: -4.4119
Max Act: 4.0056. Min Act: -0.1700
Data Index: 1182416 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19