Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2747 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.2983. Min Act: -0.1700
Data Index: 3092105 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.2512. Min Act: -0.1700
Data Index: 7857241 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.2040. Min Act: -0.1700
Data Index: 979237 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.1726. Min Act: -0.1700
Data Index: 1616878 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.1726. Min Act: -0.1700
Data Index: 2509522 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.1726. Min Act: -0.1700
Data Index: 2849518 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.1568. Min Act: -0.1700
Data Index: 8000414 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.1568. Min Act: -0.1700
Data Index: 4413296 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.1411. Min Act: -0.1700
Data Index: 2715193 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.1411. Min Act: -0.1700
Data Index: 82407 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0938. Min Act: -0.1700
Data Index: 2483139 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0781. Min Act: -0.1700
Data Index: 2539271 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0781. Min Act: -0.1700
Data Index: 82405 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0781. Min Act: -0.1700
Data Index: 7077518 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0781. Min Act: -0.1700
Data Index: 4242947 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0781. Min Act: -0.1700
Data Index: 1396831 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0781. Min Act: -0.1700
Data Index: 5970290 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0623. Min Act: -0.1700
Data Index: 3486421 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0623. Min Act: -0.1700
Data Index: 6036351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2983. Min Range: -3.2983
Max Act: 3.0623. Min Act: -0.1700
Data Index: 2985824 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19