Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6134 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.9764. Min Act: -0.1700
Data Index: 4856486 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.7889. Min Act: -0.1700
Data Index: 7931112 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.5702. Min Act: -0.1700
Data Index: 6168560 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.5389. Min Act: -0.1700
Data Index: 3533102 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.3202. Min Act: -0.1700
Data Index: 7338505 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.2889. Min Act: -0.1700
Data Index: 7212630 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.2264. Min Act: -0.1700
Data Index: 7254697 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1952. Min Act: -0.1700
Data Index: 6887611 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1952. Min Act: -0.1700
Data Index: 7830064 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.2264. Min Act: -0.1700
Data Index: 7506489 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1639. Min Act: -0.1700
Data Index: 7753286 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1952. Min Act: -0.1700
Data Index: 6930283 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1952. Min Act: -0.1700
Data Index: 7860224 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1952. Min Act: -0.1700
Data Index: 2027189 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1639. Min Act: -0.1700
Data Index: 5053533 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1327. Min Act: -0.1700
Data Index: 880087 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1014. Min Act: -0.1700
Data Index: 7830068 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1014. Min Act: -0.1700
Data Index: 6920963 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.0702. Min Act: -0.1700
Data Index: 5555758 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9764. Min Range: -7.9764
Max Act: 7.1014. Min Act: -0.1700
Data Index: 8248976 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19