Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4283 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.8664. Min Act: -0.1700
Data Index: 4450999 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.7726. Min Act: -0.1700
Data Index: 4063967 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.7726. Min Act: -0.1700
Data Index: 1650298 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.7414. Min Act: -0.1700
Data Index: 7039624 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.7726. Min Act: -0.1700
Data Index: 7087895 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6789. Min Act: -0.1700
Data Index: 3401583 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.7101. Min Act: -0.1700
Data Index: 3414556 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.7101. Min Act: -0.1700
Data Index: 1736904 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6476. Min Act: -0.1700
Data Index: 6280562 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6789. Min Act: -0.1700
Data Index: 2441856 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6789. Min Act: -0.1700
Data Index: 6409558 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6789. Min Act: -0.1700
Data Index: 5198835 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6789. Min Act: -0.1700
Data Index: 8051096 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6789. Min Act: -0.1700
Data Index: 4339704 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6476. Min Act: -0.1700
Data Index: 1144496 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6476. Min Act: -0.1700
Data Index: 7900937 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6476. Min Act: -0.1700
Data Index: 4393455 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6476. Min Act: -0.1700
Data Index: 301756 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6164. Min Act: -0.1700
Data Index: 1077445 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8664. Min Range: -4.8664
Max Act: 4.6164. Min Act: -0.1700
Data Index: 6231757 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19