Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.4800. Min Act: -0.1700
Data Index: 7849014 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.4175. Min Act: -0.1700
Data Index: 2316237 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.4175. Min Act: -0.1700
Data Index: 7927540 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3862. Min Act: -0.1700
Data Index: 4535372 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3550. Min Act: -0.1700
Data Index: 4303738 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3550. Min Act: -0.1700
Data Index: 2316239 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3862. Min Act: -0.1700
Data Index: 7528154 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3550. Min Act: -0.1700
Data Index: 2864719 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3550. Min Act: -0.1700
Data Index: 2316238 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3550. Min Act: -0.1700
Data Index: 709775 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3550. Min Act: -0.1700
Data Index: 5642633 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3237. Min Act: -0.1700
Data Index: 8370697 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3237. Min Act: -0.1700
Data Index: 1912480 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3237. Min Act: -0.1700
Data Index: 2952130 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.3237. Min Act: -0.1700
Data Index: 4613970 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.2925. Min Act: -0.1700
Data Index: 4982204 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.2925. Min Act: -0.1700
Data Index: 5205016 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.2925. Min Act: -0.1700
Data Index: 4262693 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.2925. Min Act: -0.1700
Data Index: 6762618 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4800. Min Range: -4.4800
Max Act: 4.2300. Min Act: -0.1700
Data Index: 5050259 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19