Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3702 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0357. Min Range: -7.0357
Max Act: 7.0357. Min Act: -0.1700
Data Index: 3171702 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.9107. Min Act: -0.1700
Data Index: 2707043 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.8482. Min Act: -0.1700
Data Index: 4582484 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.7857. Min Act: -0.1700
Data Index: 2076167 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.7544. Min Act: -0.1700
Data Index: 6541608 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.6607. Min Act: -0.1700
Data Index: 7844670 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.5982. Min Act: -0.1700
Data Index: 7252966 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.5044. Min Act: -0.1700
Data Index: 3306958 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.5669. Min Act: -0.1700
Data Index: 5802446 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.4732. Min Act: -0.1700
Data Index: 8006354 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.5044. Min Act: -0.1700
Data Index: 8415581 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.5044. Min Act: -0.1700
Data Index: 437190 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.4107. Min Act: -0.1700
Data Index: 4801849 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.4107. Min Act: -0.1700
Data Index: 2326737 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.3794. Min Act: -0.1700
Data Index: 1448978 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.3794. Min Act: -0.1700
Data Index: 202778 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.3794. Min Act: -0.1700
Data Index: 501521 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.3794. Min Act: -0.1700
Data Index: 1695463 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.3482. Min Act: -0.1700
Data Index: 200875 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0357. Min Range: -7.0357
Max Act: 6.3169. Min Act: -0.1700
Data Index: 4175489 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19