Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4726 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.8474. Min Act: -0.1700
Data Index: 1019288 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.8162. Min Act: -0.1700
Data Index: 7305353 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.7849. Min Act: -0.1700
Data Index: 8626857 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.7224. Min Act: -0.1700
Data Index: 3653767 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.6912. Min Act: -0.1700
Data Index: 1318528 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.6287. Min Act: -0.1700
Data Index: 2012465 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.6287. Min Act: -0.1700
Data Index: 4423013 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.6287. Min Act: -0.1700
Data Index: 6704791 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.5662. Min Act: -0.1700
Data Index: 8396729 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.5037. Min Act: -0.1700
Data Index: 8109666 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.4724. Min Act: -0.1700
Data Index: 427636 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.4099. Min Act: -0.1700
Data Index: 7535040 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.4099. Min Act: -0.1700
Data Index: 8007393 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.3787. Min Act: -0.1700
Data Index: 89834 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.3787. Min Act: -0.1700
Data Index: 3075110 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.3787. Min Act: -0.1700
Data Index: 3038058 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.3787. Min Act: -0.1700
Data Index: 6692675 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.3787. Min Act: -0.1700
Data Index: 3411479 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.3787. Min Act: -0.1700
Data Index: 5278901 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8474. Min Range: -5.8474
Max Act: 5.3787. Min Act: -0.1700
Data Index: 2762773 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19