Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1280. Min Range: -5.1280
Max Act: 5.1280. Min Act: -0.1700
Data Index: 2313359 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1280. Min Range: -5.1280
Max Act: 5.0655. Min Act: -0.1700
Data Index: 6358980 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1280. Min Range: -5.1280
Max Act: 5.0030. Min Act: -0.1700
Data Index: 4959538 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1280. Min Range: -5.1280
Max Act: 5.0030. Min Act: -0.1700
Data Index: 5409122 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.9092. Min Act: -0.1700
Data Index: 5079044 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.9092. Min Act: -0.1700
Data Index: 6421830 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.9092. Min Act: -0.1700
Data Index: 7126157 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8780. Min Act: -0.1700
Data Index: 2884526 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8780. Min Act: -0.1700
Data Index: 851246 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8780. Min Act: -0.1700
Data Index: 234709 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8467. Min Act: -0.1700
Data Index: 3849455 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8467. Min Act: -0.1700
Data Index: 7677509 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8467. Min Act: -0.1700
Data Index: 3147755 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8467. Min Act: -0.1700
Data Index: 4565852 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8467. Min Act: -0.1700
Data Index: 1546878 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8155. Min Act: -0.1700
Data Index: 5939203 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8155. Min Act: -0.1700
Data Index: 8530290 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8155. Min Act: -0.1700
Data Index: 8543879 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8155. Min Act: -0.1700
Data Index: 7873156 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1280. Min Range: -5.1280
Max Act: 4.8155. Min Act: -0.1700
Data Index: 1822397 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19