Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4506 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4332. Min Range: -5.4332
Max Act: 5.4332. Min Act: -0.1700
Data Index: 5624623 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4332. Min Range: -5.4332
Max Act: 5.3082. Min Act: -0.1700
Data Index: 7630033 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4332. Min Range: -5.4332
Max Act: 5.2769. Min Act: -0.1700
Data Index: 342426 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4332. Min Range: -5.4332
Max Act: 5.2144. Min Act: -0.1700
Data Index: 471493 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4332. Min Range: -5.4332
Max Act: 5.1832. Min Act: -0.1700
Data Index: 438852 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4332. Min Range: -5.4332
Max Act: 5.1519. Min Act: -0.1700
Data Index: 175938 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4332. Min Range: -5.4332
Max Act: 5.0894. Min Act: -0.1700
Data Index: 4311496 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9957. Min Act: -0.1700
Data Index: 2146320 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4332. Min Range: -5.4332
Max Act: 5.0269. Min Act: -0.1700
Data Index: 5218606 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9957. Min Act: -0.1700
Data Index: 3560826 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9019. Min Act: -0.1700
Data Index: 7345733 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9332. Min Act: -0.1700
Data Index: 7330042 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9644. Min Act: -0.1700
Data Index: 738131 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9332. Min Act: -0.1700
Data Index: 4591822 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9332. Min Act: -0.1700
Data Index: 4537161 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9019. Min Act: -0.1700
Data Index: 2157835 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.9019. Min Act: -0.1700
Data Index: 2117663 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.8707. Min Act: -0.1700
Data Index: 716750 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.8707. Min Act: -0.1700
Data Index: 2513662 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4332. Min Range: -5.4332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 4335392 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19